Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3455 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2967. Min Range: -7.2967
Max Act: 7.2967. Min Act: -0.1700
Data Index: 6036801 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2967. Min Range: -7.2967
Max Act: 7.2030. Min Act: -0.1700
Data Index: 4465726 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2967. Min Range: -7.2967
Max Act: 6.9530. Min Act: -0.1700
Data Index: 1490812 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2967. Min Range: -7.2967
Max Act: 6.9217. Min Act: -0.1700
Data Index: 5166451 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2967. Min Range: -7.2967
Max Act: 6.8592. Min Act: -0.1700
Data Index: 8096140 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2967. Min Range: -7.2967
Max Act: 6.7655. Min Act: -0.1700
Data Index: 2230535 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2967. Min Range: -7.2967
Max Act: 6.7655. Min Act: -0.1700
Data Index: 8151091 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2967. Min Range: -7.2967
Max Act: 6.7655. Min Act: -0.1700
Data Index: 7054041 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2967. Min Range: -7.2967
Max Act: 6.7030. Min Act: -0.1700
Data Index: 3537673 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2967. Min Range: -7.2967
Max Act: 6.7030. Min Act: -0.1700
Data Index: 5832013 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2967. Min Range: -7.2967
Max Act: 6.6405. Min Act: -0.1700
Data Index: 5878536 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2967. Min Range: -7.2967
Max Act: 6.6405. Min Act: -0.1700
Data Index: 1533002 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2967. Min Range: -7.2967
Max Act: 6.6405. Min Act: -0.1700
Data Index: 1194862 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2967. Min Range: -7.2967
Max Act: 6.6717. Min Act: -0.1700
Data Index: 6986962 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2967. Min Range: -7.2967
Max Act: 6.6405. Min Act: -0.1700
Data Index: 7172315 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2967. Min Range: -7.2967
Max Act: 6.6092. Min Act: -0.1700
Data Index: 7336364 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2967. Min Range: -7.2967
Max Act: 6.6092. Min Act: -0.1700
Data Index: 8485433 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2967. Min Range: -7.2967
Max Act: 6.6092. Min Act: -0.1700
Data Index: 4912927 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2967. Min Range: -7.2967
Max Act: 6.5780. Min Act: -0.1700
Data Index: 7169183 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2967. Min Range: -7.2967
Max Act: 6.5780. Min Act: -0.1700
Data Index: 244600 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19