Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2723 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9364. Min Range: -7.9364
Max Act: 7.9364. Min Act: -0.1700
Data Index: 4445042 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9364. Min Range: -7.9364
Max Act: 7.5302. Min Act: -0.1700
Data Index: 267455 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9364. Min Range: -7.9364
Max Act: 7.5614. Min Act: -0.1700
Data Index: 3256512 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9364. Min Range: -7.9364
Max Act: 7.0927. Min Act: -0.1700
Data Index: 3973120 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9364. Min Range: -7.9364
Max Act: 7.1552. Min Act: -0.1700
Data Index: 2511862 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9364. Min Range: -7.9364
Max Act: 7.1239. Min Act: -0.1700
Data Index: 742287 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9364. Min Range: -7.9364
Max Act: 7.1239. Min Act: -0.1700
Data Index: 8081663 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9364. Min Range: -7.9364
Max Act: 7.0614. Min Act: -0.1700
Data Index: 8042526 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9364. Min Range: -7.9364
Max Act: 7.0302. Min Act: -0.1700
Data Index: 267456 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9364. Min Range: -7.9364
Max Act: 6.9989. Min Act: -0.1700
Data Index: 786914 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9364. Min Range: -7.9364
Max Act: 6.9677. Min Act: -0.1700
Data Index: 4490613 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9364. Min Range: -7.9364
Max Act: 6.9677. Min Act: -0.1700
Data Index: 5646401 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9364. Min Range: -7.9364
Max Act: 6.8114. Min Act: -0.1700
Data Index: 3061031 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9364. Min Range: -7.9364
Max Act: 6.8114. Min Act: -0.1700
Data Index: 7424363 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9364. Min Range: -7.9364
Max Act: 6.7489. Min Act: -0.1700
Data Index: 5696603 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9364. Min Range: -7.9364
Max Act: 6.7489. Min Act: -0.1700
Data Index: 899943 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9364. Min Range: -7.9364
Max Act: 6.7177. Min Act: -0.1700
Data Index: 262499 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9364. Min Range: -7.9364
Max Act: 6.7802. Min Act: -0.1700
Data Index: 7452206 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9364. Min Range: -7.9364
Max Act: 6.7177. Min Act: -0.1700
Data Index: 805947 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9364. Min Range: -7.9364
Max Act: 6.7177. Min Act: -0.1700
Data Index: 3540348 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19