Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2905 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3491. Min Range: -7.3491
Max Act: 7.3491. Min Act: -0.1700
Data Index: 6727749 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3491. Min Range: -7.3491
Max Act: 7.0991. Min Act: -0.1700
Data Index: 689820 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3491. Min Range: -7.3491
Max Act: 7.0991. Min Act: -0.1700
Data Index: 2289400 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3491. Min Range: -7.3491
Max Act: 7.0679. Min Act: -0.1700
Data Index: 6612646 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3491. Min Range: -7.3491
Max Act: 7.0679. Min Act: -0.1700
Data Index: 3176017 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3491. Min Range: -7.3491
Max Act: 6.9741. Min Act: -0.1700
Data Index: 8076972 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3491. Min Range: -7.3491
Max Act: 6.9741. Min Act: -0.1700
Data Index: 2594091 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3491. Min Range: -7.3491
Max Act: 6.8491. Min Act: -0.1700
Data Index: 8816422 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3491. Min Range: -7.3491
Max Act: 6.8179. Min Act: -0.1700
Data Index: 1289895 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3491. Min Range: -7.3491
Max Act: 6.8179. Min Act: -0.1700
Data Index: 83232 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3491. Min Range: -7.3491
Max Act: 6.8179. Min Act: -0.1700
Data Index: 5891198 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3491. Min Range: -7.3491
Max Act: 6.8179. Min Act: -0.1700
Data Index: 3686759 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3491. Min Range: -7.3491
Max Act: 6.7866. Min Act: -0.1700
Data Index: 3311753 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3491. Min Range: -7.3491
Max Act: 6.7866. Min Act: -0.1700
Data Index: 7662970 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3491. Min Range: -7.3491
Max Act: 6.7554. Min Act: -0.1700
Data Index: 2389392 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3491. Min Range: -7.3491
Max Act: 6.7554. Min Act: -0.1700
Data Index: 494838 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3491. Min Range: -7.3491
Max Act: 6.7241. Min Act: -0.1700
Data Index: 8086184 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3491. Min Range: -7.3491
Max Act: 6.7241. Min Act: -0.1700
Data Index: 7941245 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3491. Min Range: -7.3491
Max Act: 6.7241. Min Act: -0.1700
Data Index: 6715701 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3491. Min Range: -7.3491
Max Act: 6.6304. Min Act: -0.1700
Data Index: 6239167 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19