Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 147 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6695. Min Range: -4.6695
Max Act: 4.6695. Min Act: -0.1700
Data Index: 7102395 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6695. Min Range: -4.6695
Max Act: 4.4820. Min Act: -0.1700
Data Index: 6746987 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6695. Min Range: -4.6695
Max Act: 4.4820. Min Act: -0.1700
Data Index: 5349691 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6695. Min Range: -4.6695
Max Act: 4.4507. Min Act: -0.1700
Data Index: 7242216 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6695. Min Range: -4.6695
Max Act: 4.4195. Min Act: -0.1700
Data Index: 3164648 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6695. Min Range: -4.6695
Max Act: 4.3882. Min Act: -0.1700
Data Index: 2763350 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6695. Min Range: -4.6695
Max Act: 4.3570. Min Act: -0.1700
Data Index: 8803729 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6695. Min Range: -4.6695
Max Act: 4.3570. Min Act: -0.1700
Data Index: 7077379 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6695. Min Range: -4.6695
Max Act: 4.3257. Min Act: -0.1700
Data Index: 1051767 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6695. Min Range: -4.6695
Max Act: 4.3257. Min Act: -0.1700
Data Index: 823128 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6695. Min Range: -4.6695
Max Act: 4.3257. Min Act: -0.1700
Data Index: 2270553 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6695. Min Range: -4.6695
Max Act: 4.2945. Min Act: -0.1700
Data Index: 4397125 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6695. Min Range: -4.6695
Max Act: 4.3257. Min Act: -0.1700
Data Index: 775613 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6695. Min Range: -4.6695
Max Act: 4.2945. Min Act: -0.1700
Data Index: 1059357 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6695. Min Range: -4.6695
Max Act: 4.2945. Min Act: -0.1700
Data Index: 2340432 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6695. Min Range: -4.6695
Max Act: 4.2632. Min Act: -0.1700
Data Index: 5184180 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6695. Min Range: -4.6695
Max Act: 4.2632. Min Act: -0.1700
Data Index: 1955204 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6695. Min Range: -4.6695
Max Act: 4.2632. Min Act: -0.1700
Data Index: 890990 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6695. Min Range: -4.6695
Max Act: 4.2632. Min Act: -0.1700
Data Index: 1958989 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6695. Min Range: -4.6695
Max Act: 4.2320. Min Act: -0.1700
Data Index: 3276323 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19