Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3306 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3948. Min Range: -4.3948
Max Act: 4.3948. Min Act: -0.1700
Data Index: 3269455 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3948. Min Range: -4.3948
Max Act: 4.3948. Min Act: -0.1700
Data Index: 230114 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3948. Min Range: -4.3948
Max Act: 4.3636. Min Act: -0.1700
Data Index: 4410473 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3948. Min Range: -4.3948
Max Act: 4.3323. Min Act: -0.1700
Data Index: 5901935 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3948. Min Range: -4.3948
Max Act: 4.3011. Min Act: -0.1700
Data Index: 3236925 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3948. Min Range: -4.3948
Max Act: 4.1761. Min Act: -0.1700
Data Index: 7223257 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3948. Min Range: -4.3948
Max Act: 4.1448. Min Act: -0.1700
Data Index: 5881295 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3948. Min Range: -4.3948
Max Act: 4.0823. Min Act: -0.1700
Data Index: 8403936 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3948. Min Range: -4.3948
Max Act: 4.0823. Min Act: -0.1700
Data Index: 8061893 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3948. Min Range: -4.3948
Max Act: 4.0823. Min Act: -0.1700
Data Index: 353213 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3948. Min Range: -4.3948
Max Act: 4.0510. Min Act: -0.1700
Data Index: 4074151 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3948. Min Range: -4.3948
Max Act: 4.0510. Min Act: -0.1700
Data Index: 5919774 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3948. Min Range: -4.3948
Max Act: 4.0198. Min Act: -0.1700
Data Index: 1065687 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3948. Min Range: -4.3948
Max Act: 4.0198. Min Act: -0.1700
Data Index: 8770717 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3948. Min Range: -4.3948
Max Act: 4.0510. Min Act: -0.1700
Data Index: 1653622 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3948. Min Range: -4.3948
Max Act: 4.0510. Min Act: -0.1700
Data Index: 2630198 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3948. Min Range: -4.3948
Max Act: 4.0510. Min Act: -0.1700
Data Index: 3782586 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3948. Min Range: -4.3948
Max Act: 3.9885. Min Act: -0.1700
Data Index: 6920739 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3948. Min Range: -4.3948
Max Act: 3.9885. Min Act: -0.1700
Data Index: 2686860 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3948. Min Range: -4.3948
Max Act: 3.9885. Min Act: -0.1700
Data Index: 5237744 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19