Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3590 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6175. Min Range: -8.6175
Max Act: 8.6175. Min Act: -0.1700
Data Index: 3924882 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6175. Min Range: -8.6175
Max Act: 8.1175. Min Act: -0.1700
Data Index: 812125 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6175. Min Range: -8.6175
Max Act: 7.9300. Min Act: -0.1700
Data Index: 8667490 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6175. Min Range: -8.6175
Max Act: 7.8675. Min Act: -0.1700
Data Index: 2795569 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6175. Min Range: -8.6175
Max Act: 7.8363. Min Act: -0.1700
Data Index: 7825161 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6175. Min Range: -8.6175
Max Act: 7.8363. Min Act: -0.1700
Data Index: 7400880 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6175. Min Range: -8.6175
Max Act: 7.8050. Min Act: -0.1700
Data Index: 8239300 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6175. Min Range: -8.6175
Max Act: 7.8050. Min Act: -0.1700
Data Index: 3726048 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6175. Min Range: -8.6175
Max Act: 7.7738. Min Act: -0.1700
Data Index: 96299 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6175. Min Range: -8.6175
Max Act: 7.7425. Min Act: -0.1700
Data Index: 8131863 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6175. Min Range: -8.6175
Max Act: 7.7738. Min Act: -0.1700
Data Index: 431798 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6175. Min Range: -8.6175
Max Act: 7.7425. Min Act: -0.1700
Data Index: 5956567 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6175. Min Range: -8.6175
Max Act: 7.7113. Min Act: -0.1700
Data Index: 4923489 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6175. Min Range: -8.6175
Max Act: 7.7113. Min Act: -0.1700
Data Index: 5009833 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6175. Min Range: -8.6175
Max Act: 7.6488. Min Act: -0.1700
Data Index: 1842431 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6175. Min Range: -8.6175
Max Act: 7.6488. Min Act: -0.1700
Data Index: 384304 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6175. Min Range: -8.6175
Max Act: 7.6488. Min Act: -0.1700
Data Index: 5566749 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6175. Min Range: -8.6175
Max Act: 7.6175. Min Act: -0.1700
Data Index: 8569170 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6175. Min Range: -8.6175
Max Act: 7.5863. Min Act: -0.1700
Data Index: 8341799 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6175. Min Range: -8.6175
Max Act: 7.5550. Min Act: -0.1700
Data Index: 4420622 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #19