Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3413 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6076. Min Range: -8.6076
Max Act: 8.6076. Min Act: -0.1700
Data Index: 7780572 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6076. Min Range: -8.6076
Max Act: 8.5451. Min Act: -0.1700
Data Index: 3153829 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6076. Min Range: -8.6076
Max Act: 8.4826. Min Act: -0.1700
Data Index: 2351900 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6076. Min Range: -8.6076
Max Act: 8.4826. Min Act: -0.1700
Data Index: 5950996 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6076. Min Range: -8.6076
Max Act: 8.4201. Min Act: -0.1700
Data Index: 3245679 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6076. Min Range: -8.6076
Max Act: 8.3576. Min Act: -0.1700
Data Index: 3926615 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6076. Min Range: -8.6076
Max Act: 8.3576. Min Act: -0.1700
Data Index: 3479686 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6076. Min Range: -8.6076
Max Act: 8.2951. Min Act: -0.1700
Data Index: 8160227 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6076. Min Range: -8.6076
Max Act: 8.2951. Min Act: -0.1700
Data Index: 308147 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6076. Min Range: -8.6076
Max Act: 8.2951. Min Act: -0.1700
Data Index: 8656749 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6076. Min Range: -8.6076
Max Act: 8.2951. Min Act: -0.1700
Data Index: 6397980 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6076. Min Range: -8.6076
Max Act: 8.1701. Min Act: -0.1700
Data Index: 7724608 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6076. Min Range: -8.6076
Max Act: 8.2326. Min Act: -0.1700
Data Index: 587728 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6076. Min Range: -8.6076
Max Act: 8.2326. Min Act: -0.1700
Data Index: 8393714 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6076. Min Range: -8.6076
Max Act: 8.2326. Min Act: -0.1700
Data Index: 4330894 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6076. Min Range: -8.6076
Max Act: 8.1701. Min Act: -0.1700
Data Index: 6632299 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6076. Min Range: -8.6076
Max Act: 8.1701. Min Act: -0.1700
Data Index: 5353588 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6076. Min Range: -8.6076
Max Act: 8.1701. Min Act: -0.1700
Data Index: 1876463 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6076. Min Range: -8.6076
Max Act: 8.1076. Min Act: -0.1700
Data Index: 4987515 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6076. Min Range: -8.6076
Max Act: 8.1076. Min Act: -0.1700
Data Index: 7693394 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19