Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4963 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6951. Min Range: -7.6951
Max Act: 7.6951. Min Act: -0.1700
Data Index: 2743927 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6951. Min Range: -7.6951
Max Act: 7.6639. Min Act: -0.1700
Data Index: 2825480 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6951. Min Range: -7.6951
Max Act: 7.6639. Min Act: -0.1700
Data Index: 2743914 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6951. Min Range: -7.6951
Max Act: 7.5389. Min Act: -0.1700
Data Index: 2825468 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6951. Min Range: -7.6951
Max Act: 7.5076. Min Act: -0.1700
Data Index: 8585606 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6951. Min Range: -7.6951
Max Act: 7.4764. Min Act: -0.1700
Data Index: 6516688 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6951. Min Range: -7.6951
Max Act: 7.4451. Min Act: -0.1700
Data Index: 348978 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6951. Min Range: -7.6951
Max Act: 7.4139. Min Act: -0.1700
Data Index: 3539596 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6951. Min Range: -7.6951
Max Act: 7.4139. Min Act: -0.1700
Data Index: 8085992 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6951. Min Range: -7.6951
Max Act: 7.3826. Min Act: -0.1700
Data Index: 6431138 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6951. Min Range: -7.6951
Max Act: 7.3826. Min Act: -0.1700
Data Index: 3469147 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6951. Min Range: -7.6951
Max Act: 7.3514. Min Act: -0.1700
Data Index: 4464712 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6951. Min Range: -7.6951
Max Act: 7.3514. Min Act: -0.1700
Data Index: 4847351 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6951. Min Range: -7.6951
Max Act: 7.3514. Min Act: -0.1700
Data Index: 3612933 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6951. Min Range: -7.6951
Max Act: 7.2889. Min Act: -0.1700
Data Index: 8267712 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6951. Min Range: -7.6951
Max Act: 7.2264. Min Act: -0.1700
Data Index: 2104880 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6951. Min Range: -7.6951
Max Act: 7.2264. Min Act: -0.1700
Data Index: 5268583 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6951. Min Range: -7.6951
Max Act: 7.1639. Min Act: -0.1700
Data Index: 7868227 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6951. Min Range: -7.6951
Max Act: 7.1639. Min Act: -0.1700
Data Index: 6669795 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6951. Min Range: -7.6951
Max Act: 7.1326. Min Act: -0.1700
Data Index: 3075669 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19