Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1166 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3301. Min Range: -5.3301
Max Act: 5.3301. Min Act: -0.1700
Data Index: 3595003 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3301. Min Range: -5.3301
Max Act: 5.0176. Min Act: -0.1700
Data Index: 2864827 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3301. Min Range: -5.3301
Max Act: 4.9238. Min Act: -0.1700
Data Index: 4951338 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3301. Min Range: -5.3301
Max Act: 4.8301. Min Act: -0.1700
Data Index: 7611747 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3301. Min Range: -5.3301
Max Act: 4.7988. Min Act: -0.1700
Data Index: 4929076 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3301. Min Range: -5.3301
Max Act: 4.7988. Min Act: -0.1700
Data Index: 6824308 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3301. Min Range: -5.3301
Max Act: 4.7988. Min Act: -0.1700
Data Index: 963611 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3301. Min Range: -5.3301
Max Act: 4.7676. Min Act: -0.1700
Data Index: 8336430 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3301. Min Range: -5.3301
Max Act: 4.7363. Min Act: -0.1700
Data Index: 3337100 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3301. Min Range: -5.3301
Max Act: 4.7363. Min Act: -0.1700
Data Index: 3186648 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3301. Min Range: -5.3301
Max Act: 4.7051. Min Act: -0.1700
Data Index: 4281821 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3301. Min Range: -5.3301
Max Act: 4.7363. Min Act: -0.1700
Data Index: 2229662 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3301. Min Range: -5.3301
Max Act: 4.7363. Min Act: -0.1700
Data Index: 5110524 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3301. Min Range: -5.3301
Max Act: 4.7363. Min Act: -0.1700
Data Index: 2811160 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3301. Min Range: -5.3301
Max Act: 4.7363. Min Act: -0.1700
Data Index: 8580535 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3301. Min Range: -5.3301
Max Act: 4.7051. Min Act: -0.1700
Data Index: 2966397 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3301. Min Range: -5.3301
Max Act: 4.7051. Min Act: -0.1700
Data Index: 568988 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3301. Min Range: -5.3301
Max Act: 4.7051. Min Act: -0.1700
Data Index: 3237016 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3301. Min Range: -5.3301
Max Act: 4.7051. Min Act: -0.1700
Data Index: 1058239 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3301. Min Range: -5.3301
Max Act: 4.7051. Min Act: -0.1700
Data Index: 6449192 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19