Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2615 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0259. Min Range: -4.0259
Max Act: 4.0259. Min Act: -0.1700
Data Index: 8797204 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0259. Min Range: -4.0259
Max Act: 4.0259. Min Act: -0.1700
Data Index: 3269585 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0259. Min Range: -4.0259
Max Act: 3.9164. Min Act: -0.1700
Data Index: 984536 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0259. Min Range: -4.0259
Max Act: 3.9008. Min Act: -0.1700
Data Index: 3918522 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0259. Min Range: -4.0259
Max Act: 3.8852. Min Act: -0.1700
Data Index: 1398795 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0259. Min Range: -4.0259
Max Act: 3.8852. Min Act: -0.1700
Data Index: 7684178 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0259. Min Range: -4.0259
Max Act: 3.8852. Min Act: -0.1700
Data Index: 1157235 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0259. Min Range: -4.0259
Max Act: 3.8695. Min Act: -0.1700
Data Index: 8272100 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0259. Min Range: -4.0259
Max Act: 3.8383. Min Act: -0.1700
Data Index: 7168079 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0259. Min Range: -4.0259
Max Act: 3.8539. Min Act: -0.1700
Data Index: 6209071 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0259. Min Range: -4.0259
Max Act: 3.8383. Min Act: -0.1700
Data Index: 2986659 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0259. Min Range: -4.0259
Max Act: 3.8070. Min Act: -0.1700
Data Index: 433420 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0259. Min Range: -4.0259
Max Act: 3.8226. Min Act: -0.1700
Data Index: 745218 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0259. Min Range: -4.0259
Max Act: 3.7914. Min Act: -0.1700
Data Index: 3672787 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0259. Min Range: -4.0259
Max Act: 3.7914. Min Act: -0.1700
Data Index: 5323858 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0259. Min Range: -4.0259
Max Act: 3.7757. Min Act: -0.1700
Data Index: 4940990 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0259. Min Range: -4.0259
Max Act: 3.7601. Min Act: -0.1700
Data Index: 1051522 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0259. Min Range: -4.0259
Max Act: 3.7445. Min Act: -0.1700
Data Index: 5046491 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0259. Min Range: -4.0259
Max Act: 3.7601. Min Act: -0.1700
Data Index: 4204165 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0259. Min Range: -4.0259
Max Act: 3.7445. Min Act: -0.1700
Data Index: 7735942 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #19