Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4255 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0175. Min Range: -9.0175
Max Act: 9.0175. Min Act: -0.1700
Data Index: 1414331 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0175. Min Range: -9.0175
Max Act: 8.9550. Min Act: -0.1700
Data Index: 2036645 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0175. Min Range: -9.0175
Max Act: 8.5800. Min Act: -0.1700
Data Index: 4140558 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0175. Min Range: -9.0175
Max Act: 8.5175. Min Act: -0.1700
Data Index: 5923350 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0175. Min Range: -9.0175
Max Act: 8.4550. Min Act: -0.1700
Data Index: 3109159 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0175. Min Range: -9.0175
Max Act: 8.3925. Min Act: -0.1700
Data Index: 8827297 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0175. Min Range: -9.0175
Max Act: 8.3925. Min Act: -0.1700
Data Index: 2143827 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0175. Min Range: -9.0175
Max Act: 8.3300. Min Act: -0.1700
Data Index: 3650252 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0175. Min Range: -9.0175
Max Act: 8.3300. Min Act: -0.1700
Data Index: 1649292 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0175. Min Range: -9.0175
Max Act: 8.3300. Min Act: -0.1700
Data Index: 4130092 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0175. Min Range: -9.0175
Max Act: 8.3300. Min Act: -0.1700
Data Index: 4473927 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0175. Min Range: -9.0175
Max Act: 8.3300. Min Act: -0.1700
Data Index: 6917994 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0175. Min Range: -9.0175
Max Act: 8.2050. Min Act: -0.1700
Data Index: 4178737 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0175. Min Range: -9.0175
Max Act: 8.2050. Min Act: -0.1700
Data Index: 1706173 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0175. Min Range: -9.0175
Max Act: 8.2050. Min Act: -0.1700
Data Index: 2597441 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0175. Min Range: -9.0175
Max Act: 8.2050. Min Act: -0.1700
Data Index: 5662713 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0175. Min Range: -9.0175
Max Act: 8.2050. Min Act: -0.1700
Data Index: 2093769 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0175. Min Range: -9.0175
Max Act: 8.1425. Min Act: -0.1700
Data Index: 2589312 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0175. Min Range: -9.0175
Max Act: 8.0800. Min Act: -0.1700
Data Index: 47205 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0175. Min Range: -9.0175
Max Act: 8.1425. Min Act: -0.1700
Data Index: 4127853 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19