Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3566 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8262. Min Range: -3.8262
Max Act: 3.8262. Min Act: -0.1700
Data Index: 8533905 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8262. Min Range: -3.8262
Max Act: 3.7949. Min Act: -0.1700
Data Index: 4866234 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8262. Min Range: -3.8262
Max Act: 3.7480. Min Act: -0.1700
Data Index: 3558270 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8262. Min Range: -3.8262
Max Act: 3.6854. Min Act: -0.1700
Data Index: 7386486 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8262. Min Range: -3.8262
Max Act: 3.7167. Min Act: -0.1700
Data Index: 5859561 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8262. Min Range: -3.8262
Max Act: 3.6698. Min Act: -0.1700
Data Index: 1942368 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8262. Min Range: -3.8262
Max Act: 3.6698. Min Act: -0.1700
Data Index: 8489978 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8262. Min Range: -3.8262
Max Act: 3.6698. Min Act: -0.1700
Data Index: 4561321 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8262. Min Range: -3.8262
Max Act: 3.6542. Min Act: -0.1700
Data Index: 7429535 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8262. Min Range: -3.8262
Max Act: 3.6385. Min Act: -0.1700
Data Index: 707748 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8262. Min Range: -3.8262
Max Act: 3.6385. Min Act: -0.1700
Data Index: 4262041 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8262. Min Range: -3.8262
Max Act: 3.6229. Min Act: -0.1700
Data Index: 5373370 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8262. Min Range: -3.8262
Max Act: 3.5916. Min Act: -0.1700
Data Index: 8787063 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8262. Min Range: -3.8262
Max Act: 3.6072. Min Act: -0.1700
Data Index: 3432344 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8262. Min Range: -3.8262
Max Act: 3.6072. Min Act: -0.1700
Data Index: 95235 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8262. Min Range: -3.8262
Max Act: 3.6072. Min Act: -0.1700
Data Index: 2272161 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8262. Min Range: -3.8262
Max Act: 3.6072. Min Act: -0.1700
Data Index: 7588427 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8262. Min Range: -3.8262
Max Act: 3.6072. Min Act: -0.1700
Data Index: 5480387 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8262. Min Range: -3.8262
Max Act: 3.6072. Min Act: -0.1700
Data Index: 1468882 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8262. Min Range: -3.8262
Max Act: 3.6072. Min Act: -0.1700
Data Index: 5919774 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19