Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3295 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8402. Min Range: -3.8402
Max Act: 3.8402. Min Act: -0.1700
Data Index: 7716518 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8402. Min Range: -3.8402
Max Act: 3.8246. Min Act: -0.1700
Data Index: 4207767 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8402. Min Range: -3.8402
Max Act: 3.8246. Min Act: -0.1700
Data Index: 7540123 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8402. Min Range: -3.8402
Max Act: 3.7464. Min Act: -0.1700
Data Index: 3244001 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8402. Min Range: -3.8402
Max Act: 3.7308. Min Act: -0.1700
Data Index: 198100 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8402. Min Range: -3.8402
Max Act: 3.7151. Min Act: -0.1700
Data Index: 5982866 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8402. Min Range: -3.8402
Max Act: 3.7308. Min Act: -0.1700
Data Index: 628882 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8402. Min Range: -3.8402
Max Act: 3.7308. Min Act: -0.1700
Data Index: 8708515 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8402. Min Range: -3.8402
Max Act: 3.6995. Min Act: -0.1700
Data Index: 8187242 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8402. Min Range: -3.8402
Max Act: 3.6995. Min Act: -0.1700
Data Index: 4204072 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8402. Min Range: -3.8402
Max Act: 3.6995. Min Act: -0.1700
Data Index: 4693453 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8402. Min Range: -3.8402
Max Act: 3.6838. Min Act: -0.1700
Data Index: 386025 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8402. Min Range: -3.8402
Max Act: 3.6682. Min Act: -0.1700
Data Index: 5916063 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8402. Min Range: -3.8402
Max Act: 3.6369. Min Act: -0.1700
Data Index: 6075158 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8402. Min Range: -3.8402
Max Act: 3.6369. Min Act: -0.1700
Data Index: 6479550 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8402. Min Range: -3.8402
Max Act: 3.6369. Min Act: -0.1700
Data Index: 6901762 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8402. Min Range: -3.8402
Max Act: 3.6369. Min Act: -0.1700
Data Index: 6597979 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8402. Min Range: -3.8402
Max Act: 3.6213. Min Act: -0.1700
Data Index: 3616768 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8402. Min Range: -3.8402
Max Act: 3.6369. Min Act: -0.1700
Data Index: 5775943 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8402. Min Range: -3.8402
Max Act: 3.6526. Min Act: -0.1700
Data Index: 8426707 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19