Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1071 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9743. Min Range: -5.9743
Max Act: 5.9743. Min Act: -0.1700
Data Index: 5024208 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9743. Min Range: -5.9743
Max Act: 5.9430. Min Act: -0.1700
Data Index: 5509610 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9743. Min Range: -5.9743
Max Act: 5.9430. Min Act: -0.1700
Data Index: 8604129 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9743. Min Range: -5.9743
Max Act: 5.9430. Min Act: -0.1700
Data Index: 6688329 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9743. Min Range: -5.9743
Max Act: 5.9118. Min Act: -0.1700
Data Index: 2204458 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9743. Min Range: -5.9743
Max Act: 5.9118. Min Act: -0.1700
Data Index: 5486712 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9743. Min Range: -5.9743
Max Act: 5.8805. Min Act: -0.1700
Data Index: 368306 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9743. Min Range: -5.9743
Max Act: 5.8805. Min Act: -0.1700
Data Index: 890002 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9743. Min Range: -5.9743
Max Act: 5.8493. Min Act: -0.1700
Data Index: 5039449 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9743. Min Range: -5.9743
Max Act: 5.8180. Min Act: -0.1700
Data Index: 817518 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9743. Min Range: -5.9743
Max Act: 5.8493. Min Act: -0.1700
Data Index: 6429551 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9743. Min Range: -5.9743
Max Act: 5.8180. Min Act: -0.1700
Data Index: 502649 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9743. Min Range: -5.9743
Max Act: 5.8180. Min Act: -0.1700
Data Index: 2850273 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9743. Min Range: -5.9743
Max Act: 5.7868. Min Act: -0.1700
Data Index: 7166831 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9743. Min Range: -5.9743
Max Act: 5.8180. Min Act: -0.1700
Data Index: 3740643 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9743. Min Range: -5.9743
Max Act: 5.7868. Min Act: -0.1700
Data Index: 7437439 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9743. Min Range: -5.9743
Max Act: 5.7868. Min Act: -0.1700
Data Index: 2779893 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9743. Min Range: -5.9743
Max Act: 5.7555. Min Act: -0.1700
Data Index: 727190 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9743. Min Range: -5.9743
Max Act: 5.7555. Min Act: -0.1700
Data Index: 321164 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9743. Min Range: -5.9743
Max Act: 5.7243. Min Act: -0.1700
Data Index: 1492918 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19