Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2432 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.1694. Min Range: -8.1694
Max Act: 8.1694. Min Act: -0.1700
Data Index: 7242069 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1694. Min Range: -8.1694
Max Act: 8.0444. Min Act: -0.1700
Data Index: 5047329 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1694. Min Range: -8.1694
Max Act: 7.9819. Min Act: -0.1700
Data Index: 2106351 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1694. Min Range: -8.1694
Max Act: 7.9194. Min Act: -0.1700
Data Index: 6903115 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1694. Min Range: -8.1694
Max Act: 7.9194. Min Act: -0.1700
Data Index: 3804494 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1694. Min Range: -8.1694
Max Act: 7.8569. Min Act: -0.1700
Data Index: 5322522 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1694. Min Range: -8.1694
Max Act: 7.8569. Min Act: -0.1700
Data Index: 1736936 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1694. Min Range: -8.1694
Max Act: 7.8569. Min Act: -0.1700
Data Index: 7865493 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1694. Min Range: -8.1694
Max Act: 7.8569. Min Act: -0.1700
Data Index: 4145241 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1694. Min Range: -8.1694
Max Act: 7.7944. Min Act: -0.1700
Data Index: 2225906 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1694. Min Range: -8.1694
Max Act: 7.7944. Min Act: -0.1700
Data Index: 4734951 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1694. Min Range: -8.1694
Max Act: 7.7944. Min Act: -0.1700
Data Index: 4395012 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1694. Min Range: -8.1694
Max Act: 7.7319. Min Act: -0.1700
Data Index: 7652962 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1694. Min Range: -8.1694
Max Act: 7.7319. Min Act: -0.1700
Data Index: 1201594 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1694. Min Range: -8.1694
Max Act: 7.7319. Min Act: -0.1700
Data Index: 4031998 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1694. Min Range: -8.1694
Max Act: 7.7319. Min Act: -0.1700
Data Index: 1273504 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1694. Min Range: -8.1694
Max Act: 7.7319. Min Act: -0.1700
Data Index: 6923158 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1694. Min Range: -8.1694
Max Act: 7.7319. Min Act: -0.1700
Data Index: 410723 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1694. Min Range: -8.1694
Max Act: 7.7319. Min Act: -0.1700
Data Index: 7160566 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1694. Min Range: -8.1694
Max Act: 7.6694. Min Act: -0.1700
Data Index: 4515351 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19