Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3895 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6520. Min Range: -4.6520
Max Act: 4.6520. Min Act: -0.1700
Data Index: 679296 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6520. Min Range: -4.6520
Max Act: 4.6208. Min Act: -0.1700
Data Index: 5179053 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6520. Min Range: -4.6520
Max Act: 4.5895. Min Act: -0.1700
Data Index: 348470 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6520. Min Range: -4.6520
Max Act: 4.5270. Min Act: -0.1700
Data Index: 6960553 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6520. Min Range: -4.6520
Max Act: 4.4958. Min Act: -0.1700
Data Index: 8362506 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6520. Min Range: -4.6520
Max Act: 4.4958. Min Act: -0.1700
Data Index: 3335968 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6520. Min Range: -4.6520
Max Act: 4.4958. Min Act: -0.1700
Data Index: 844551 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6520. Min Range: -4.6520
Max Act: 4.4958. Min Act: -0.1700
Data Index: 1674723 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6520. Min Range: -4.6520
Max Act: 4.4645. Min Act: -0.1700
Data Index: 4133992 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6520. Min Range: -4.6520
Max Act: 4.4333. Min Act: -0.1700
Data Index: 639114 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6520. Min Range: -4.6520
Max Act: 4.4333. Min Act: -0.1700
Data Index: 7419966 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6520. Min Range: -4.6520
Max Act: 4.4333. Min Act: -0.1700
Data Index: 7115369 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6520. Min Range: -4.6520
Max Act: 4.4020. Min Act: -0.1700
Data Index: 2492673 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6520. Min Range: -4.6520
Max Act: 4.4020. Min Act: -0.1700
Data Index: 7797480 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6520. Min Range: -4.6520
Max Act: 4.4020. Min Act: -0.1700
Data Index: 486879 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6520. Min Range: -4.6520
Max Act: 4.4020. Min Act: -0.1700
Data Index: 1290944 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6520. Min Range: -4.6520
Max Act: 4.3708. Min Act: -0.1700
Data Index: 7797477 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6520. Min Range: -4.6520
Max Act: 4.3708. Min Act: -0.1700
Data Index: 749473 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6520. Min Range: -4.6520
Max Act: 4.3708. Min Act: -0.1700
Data Index: 2532711 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6520. Min Range: -4.6520
Max Act: 4.3708. Min Act: -0.1700
Data Index: 3265984 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #19