Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3562 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 23.4353. Min Range: -23.4353
Max Act: 23.4353. Min Act: -0.1700
Data Index: 5710732 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 23.4353. Min Range: -23.4353
Max Act: 23.3103. Min Act: -0.1700
Data Index: 4725645 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 23.4353. Min Range: -23.4353
Max Act: 23.3103. Min Act: -0.1700
Data Index: 5710737 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 23.4353. Min Range: -23.4353
Max Act: 23.1853. Min Act: -0.1700
Data Index: 4475076 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 23.4353. Min Range: -23.4353
Max Act: 23.1853. Min Act: -0.1700
Data Index: 2572078 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 23.4353. Min Range: -23.4353
Max Act: 23.1853. Min Act: -0.1700
Data Index: 2572051 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 23.4353. Min Range: -23.4353
Max Act: 23.1853. Min Act: -0.1700
Data Index: 5710739 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 23.4353. Min Range: -23.4353
Max Act: 23.0603. Min Act: -0.1700
Data Index: 5710745 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 23.4353. Min Range: -23.4353
Max Act: 23.0603. Min Act: -0.1700
Data Index: 2572061 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 23.4353. Min Range: -23.4353
Max Act: 23.0603. Min Act: -0.1700
Data Index: 4475084 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 23.4353. Min Range: -23.4353
Max Act: 23.0603. Min Act: -0.1700
Data Index: 5710749 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 23.4353. Min Range: -23.4353
Max Act: 23.0603. Min Act: -0.1700
Data Index: 2572064 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 23.4353. Min Range: -23.4353
Max Act: 23.0603. Min Act: -0.1700
Data Index: 5710743 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 23.4353. Min Range: -23.4353
Max Act: 23.0603. Min Act: -0.1700
Data Index: 2572068 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 23.4353. Min Range: -23.4353
Max Act: 23.0603. Min Act: -0.1700
Data Index: 2572081 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 23.4353. Min Range: -23.4353
Max Act: 23.0603. Min Act: -0.1700
Data Index: 5710735 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 23.4353. Min Range: -23.4353
Max Act: 23.0603. Min Act: -0.1700
Data Index: 2572077 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 23.4353. Min Range: -23.4353
Max Act: 23.0603. Min Act: -0.1700
Data Index: 5710726 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 23.4353. Min Range: -23.4353
Max Act: 23.0603. Min Act: -0.1700
Data Index: 4725646 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 23.4353. Min Range: -23.4353
Max Act: 23.0603. Min Act: -0.1700
Data Index: 4725638 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19