Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 22 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1165. Min Range: -2.1165
Max Act: 2.1165. Min Act: -0.1700
Data Index: 1367204 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1165. Min Range: -2.1165
Max Act: 2.0830. Min Act: -0.1700
Data Index: 5891767 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1165. Min Range: -2.1165
Max Act: 2.0326. Min Act: -0.1700
Data Index: 1049867 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1165. Min Range: -2.1165
Max Act: 2.0157. Min Act: -0.1700
Data Index: 1074050 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1165. Min Range: -2.1165
Max Act: 2.0157. Min Act: -0.1700
Data Index: 8649184 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1165. Min Range: -2.1165
Max Act: 2.0157. Min Act: -0.1700
Data Index: 5486886 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1165. Min Range: -2.1165
Max Act: 2.0157. Min Act: -0.1700
Data Index: 1426241 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1165. Min Range: -2.1165
Max Act: 2.0157. Min Act: -0.1700
Data Index: 5471338 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1165. Min Range: -2.1165
Max Act: 1.9988. Min Act: -0.1700
Data Index: 7546238 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1165. Min Range: -2.1165
Max Act: 1.9819. Min Act: -0.1700
Data Index: 3943347 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1165. Min Range: -2.1165
Max Act: 1.9650. Min Act: -0.1700
Data Index: 1377262 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1165. Min Range: -2.1165
Max Act: 1.9819. Min Act: -0.1700
Data Index: 2291971 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1165. Min Range: -2.1165
Max Act: 1.9819. Min Act: -0.1700
Data Index: 4969204 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1165. Min Range: -2.1165
Max Act: 1.9819. Min Act: -0.1700
Data Index: 8545646 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1165. Min Range: -2.1165
Max Act: 1.9819. Min Act: -0.1700
Data Index: 490407 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1165. Min Range: -2.1165
Max Act: 1.9480. Min Act: -0.1700
Data Index: 5200137 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1165. Min Range: -2.1165
Max Act: 1.9650. Min Act: -0.1700
Data Index: 7635566 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1165. Min Range: -2.1165
Max Act: 1.9650. Min Act: -0.1700
Data Index: 2737609 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1165. Min Range: -2.1165
Max Act: 1.9650. Min Act: -0.1700
Data Index: 6942366 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1165. Min Range: -2.1165
Max Act: 1.9819. Min Act: -0.1700
Data Index: 5974665 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19