Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 636 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.6168. Min Act: -0.1700
Data Index: 2656168 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.5856. Min Act: -0.1700
Data Index: 3062379 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.6168. Min Act: -0.1700
Data Index: 3414192 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.5856. Min Act: -0.1700
Data Index: 5161167 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.5543. Min Act: -0.1700
Data Index: 6280481 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.5231. Min Act: -0.1700
Data Index: 3036602 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.5231. Min Act: -0.1700
Data Index: 7025516 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.5543. Min Act: -0.1700
Data Index: 2383209 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.5543. Min Act: -0.1700
Data Index: 7376546 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.5543. Min Act: -0.1700
Data Index: 8130860 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.5543. Min Act: -0.1700
Data Index: 2223680 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.5231. Min Act: -0.1700
Data Index: 5684579 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.4918. Min Act: -0.1700
Data Index: 5591068 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.5231. Min Act: -0.1700
Data Index: 418387 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.5231. Min Act: -0.1700
Data Index: 8647174 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.5231. Min Act: -0.1700
Data Index: 1518617 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.5231. Min Act: -0.1700
Data Index: 587693 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.5231. Min Act: -0.1700
Data Index: 677086 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.4606. Min Act: -0.1700
Data Index: 3735697 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.4918. Min Act: -0.1700
Data Index: 1985251 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #19