Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3657 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4253. Min Range: -4.4253
Max Act: 4.4253. Min Act: -0.1700
Data Index: 5207659 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4253. Min Range: -4.4253
Max Act: 4.3941. Min Act: -0.1700
Data Index: 5986838 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4253. Min Range: -4.4253
Max Act: 4.3628. Min Act: -0.1700
Data Index: 7576709 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4253. Min Range: -4.4253
Max Act: 4.3316. Min Act: -0.1700
Data Index: 1586033 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4253. Min Range: -4.4253
Max Act: 4.3316. Min Act: -0.1700
Data Index: 3479828 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4253. Min Range: -4.4253
Max Act: 4.3316. Min Act: -0.1700
Data Index: 4532986 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4253. Min Range: -4.4253
Max Act: 4.3628. Min Act: -0.1700
Data Index: 1895204 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4253. Min Range: -4.4253
Max Act: 4.3003. Min Act: -0.1700
Data Index: 7216845 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4253. Min Range: -4.4253
Max Act: 4.2691. Min Act: -0.1700
Data Index: 5858087 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4253. Min Range: -4.4253
Max Act: 4.3003. Min Act: -0.1700
Data Index: 2723835 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4253. Min Range: -4.4253
Max Act: 4.2691. Min Act: -0.1700
Data Index: 8619176 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4253. Min Range: -4.4253
Max Act: 4.2691. Min Act: -0.1700
Data Index: 5011262 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4253. Min Range: -4.4253
Max Act: 4.2378. Min Act: -0.1700
Data Index: 3778424 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4253. Min Range: -4.4253
Max Act: 4.2691. Min Act: -0.1700
Data Index: 6520247 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4253. Min Range: -4.4253
Max Act: 4.2378. Min Act: -0.1700
Data Index: 503358 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4253. Min Range: -4.4253
Max Act: 4.1753. Min Act: -0.1700
Data Index: 990650 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4253. Min Range: -4.4253
Max Act: 4.2065. Min Act: -0.1700
Data Index: 3375759 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4253. Min Range: -4.4253
Max Act: 4.1753. Min Act: -0.1700
Data Index: 576384 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4253. Min Range: -4.4253
Max Act: 4.1753. Min Act: -0.1700
Data Index: 3422891 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4253. Min Range: -4.4253
Max Act: 4.1440. Min Act: -0.1700
Data Index: 5183847 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #19