Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2211 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3174. Min Range: -7.3174
Max Act: 7.3174. Min Act: -0.1700
Data Index: 1543325 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3174. Min Range: -7.3174
Max Act: 6.9111. Min Act: -0.1700
Data Index: 1531298 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3174. Min Range: -7.3174
Max Act: 6.9111. Min Act: -0.1700
Data Index: 2028526 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3174. Min Range: -7.3174
Max Act: 6.9111. Min Act: -0.1700
Data Index: 1307532 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3174. Min Range: -7.3174
Max Act: 6.8486. Min Act: -0.1700
Data Index: 3703888 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3174. Min Range: -7.3174
Max Act: 6.8799. Min Act: -0.1700
Data Index: 5259254 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3174. Min Range: -7.3174
Max Act: 6.8486. Min Act: -0.1700
Data Index: 124227 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3174. Min Range: -7.3174
Max Act: 6.7861. Min Act: -0.1700
Data Index: 5223716 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3174. Min Range: -7.3174
Max Act: 6.7861. Min Act: -0.1700
Data Index: 255478 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3174. Min Range: -7.3174
Max Act: 6.7861. Min Act: -0.1700
Data Index: 1765175 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3174. Min Range: -7.3174
Max Act: 6.7236. Min Act: -0.1700
Data Index: 6582888 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3174. Min Range: -7.3174
Max Act: 6.7236. Min Act: -0.1700
Data Index: 4233740 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3174. Min Range: -7.3174
Max Act: 6.7549. Min Act: -0.1700
Data Index: 3623711 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3174. Min Range: -7.3174
Max Act: 6.7236. Min Act: -0.1700
Data Index: 2825563 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3174. Min Range: -7.3174
Max Act: 6.7236. Min Act: -0.1700
Data Index: 1569071 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3174. Min Range: -7.3174
Max Act: 6.7236. Min Act: -0.1700
Data Index: 7080941 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3174. Min Range: -7.3174
Max Act: 6.6924. Min Act: -0.1700
Data Index: 6995123 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3174. Min Range: -7.3174
Max Act: 6.6924. Min Act: -0.1700
Data Index: 2304317 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3174. Min Range: -7.3174
Max Act: 6.6924. Min Act: -0.1700
Data Index: 1005160 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3174. Min Range: -7.3174
Max Act: 6.6611. Min Act: -0.1700
Data Index: 6378132 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19