Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3432 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7695. Min Range: -5.7695
Max Act: 5.7695. Min Act: -0.1700
Data Index: 1744927 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7695. Min Range: -5.7695
Max Act: 5.6757. Min Act: -0.1700
Data Index: 3497685 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7695. Min Range: -5.7695
Max Act: 5.6445. Min Act: -0.1700
Data Index: 1820806 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7695. Min Range: -5.7695
Max Act: 5.5507. Min Act: -0.1700
Data Index: 714728 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7695. Min Range: -5.7695
Max Act: 5.5195. Min Act: -0.1700
Data Index: 8766587 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7695. Min Range: -5.7695
Max Act: 5.5195. Min Act: -0.1700
Data Index: 1677862 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7695. Min Range: -5.7695
Max Act: 5.4882. Min Act: -0.1700
Data Index: 318734 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7695. Min Range: -5.7695
Max Act: 5.5195. Min Act: -0.1700
Data Index: 3208842 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7695. Min Range: -5.7695
Max Act: 5.4570. Min Act: -0.1700
Data Index: 5706793 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7695. Min Range: -5.7695
Max Act: 5.4257. Min Act: -0.1700
Data Index: 2172055 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7695. Min Range: -5.7695
Max Act: 5.4257. Min Act: -0.1700
Data Index: 2811752 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7695. Min Range: -5.7695
Max Act: 5.4257. Min Act: -0.1700
Data Index: 1611074 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7695. Min Range: -5.7695
Max Act: 5.4257. Min Act: -0.1700
Data Index: 7007386 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7695. Min Range: -5.7695
Max Act: 5.4257. Min Act: -0.1700
Data Index: 7044714 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7695. Min Range: -5.7695
Max Act: 5.3945. Min Act: -0.1700
Data Index: 3701619 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7695. Min Range: -5.7695
Max Act: 5.3945. Min Act: -0.1700
Data Index: 142328 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7695. Min Range: -5.7695
Max Act: 5.3945. Min Act: -0.1700
Data Index: 1928481 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7695. Min Range: -5.7695
Max Act: 5.3632. Min Act: -0.1700
Data Index: 5227742 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7695. Min Range: -5.7695
Max Act: 5.3632. Min Act: -0.1700
Data Index: 6801366 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7695. Min Range: -5.7695
Max Act: 5.3632. Min Act: -0.1700
Data Index: 971123 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #19