Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2034 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7099. Min Range: -5.7099
Max Act: 5.7099. Min Act: -0.1700
Data Index: 6928700 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7099. Min Range: -5.7099
Max Act: 5.7099. Min Act: -0.1700
Data Index: 8642096 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7099. Min Range: -5.7099
Max Act: 5.7099. Min Act: -0.1700
Data Index: 8339033 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7099. Min Range: -5.7099
Max Act: 5.7099. Min Act: -0.1700
Data Index: 2120973 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7099. Min Range: -5.7099
Max Act: 5.6786. Min Act: -0.1700
Data Index: 1631194 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7099. Min Range: -5.7099
Max Act: 5.6786. Min Act: -0.1700
Data Index: 3116457 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7099. Min Range: -5.7099
Max Act: 5.6474. Min Act: -0.1700
Data Index: 5133817 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7099. Min Range: -5.7099
Max Act: 5.6474. Min Act: -0.1700
Data Index: 3498299 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7099. Min Range: -5.7099
Max Act: 5.6474. Min Act: -0.1700
Data Index: 4453096 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7099. Min Range: -5.7099
Max Act: 5.6786. Min Act: -0.1700
Data Index: 4452329 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7099. Min Range: -5.7099
Max Act: 5.6474. Min Act: -0.1700
Data Index: 7837645 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7099. Min Range: -5.7099
Max Act: 5.6474. Min Act: -0.1699
Data Index: 4398661 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7099. Min Range: -5.7099
Max Act: 5.6161. Min Act: -0.1700
Data Index: 1942842 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7099. Min Range: -5.7099
Max Act: 5.6474. Min Act: -0.1700
Data Index: 898905 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7099. Min Range: -5.7099
Max Act: 5.6474. Min Act: -0.1700
Data Index: 6535029 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7099. Min Range: -5.7099
Max Act: 5.5849. Min Act: -0.1700
Data Index: 343639 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7099. Min Range: -5.7099
Max Act: 5.6474. Min Act: -0.1700
Data Index: 7259828 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7099. Min Range: -5.7099
Max Act: 5.6161. Min Act: -0.1700
Data Index: 2870941 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7099. Min Range: -5.7099
Max Act: 5.6161. Min Act: -0.1700
Data Index: 6985937 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7099. Min Range: -5.7099
Max Act: 5.6161. Min Act: -0.1700
Data Index: 1083662 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #19