Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4502 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5451. Min Range: -6.5451
Max Act: 6.5451. Min Act: -0.1700
Data Index: 5195014 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5451. Min Range: -6.5451
Max Act: 6.4201. Min Act: -0.1700
Data Index: 3782523 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5451. Min Range: -6.5451
Max Act: 6.1389. Min Act: -0.1700
Data Index: 7374024 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5451. Min Range: -6.5451
Max Act: 6.1076. Min Act: -0.1700
Data Index: 5682539 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5451. Min Range: -6.5451
Max Act: 6.0764. Min Act: -0.1700
Data Index: 3266041 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5451. Min Range: -6.5451
Max Act: 6.0451. Min Act: -0.1700
Data Index: 2446337 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5451. Min Range: -6.5451
Max Act: 6.0451. Min Act: -0.1700
Data Index: 4212645 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5451. Min Range: -6.5451
Max Act: 6.0451. Min Act: -0.1700
Data Index: 1962564 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5451. Min Range: -6.5451
Max Act: 6.0451. Min Act: -0.1700
Data Index: 8256393 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5451. Min Range: -6.5451
Max Act: 6.0139. Min Act: -0.1700
Data Index: 814822 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5451. Min Range: -6.5451
Max Act: 5.9826. Min Act: -0.1700
Data Index: 1485996 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5451. Min Range: -6.5451
Max Act: 5.9826. Min Act: -0.1700
Data Index: 7456172 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5451. Min Range: -6.5451
Max Act: 5.9514. Min Act: -0.1700
Data Index: 4089804 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5451. Min Range: -6.5451
Max Act: 5.9514. Min Act: -0.1700
Data Index: 5079527 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5451. Min Range: -6.5451
Max Act: 5.9201. Min Act: -0.1700
Data Index: 8188896 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5451. Min Range: -6.5451
Max Act: 5.8889. Min Act: -0.1700
Data Index: 6610826 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5451. Min Range: -6.5451
Max Act: 5.9201. Min Act: -0.1700
Data Index: 4928751 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5451. Min Range: -6.5451
Max Act: 5.8889. Min Act: -0.1700
Data Index: 5195013 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5451. Min Range: -6.5451
Max Act: 5.8889. Min Act: -0.1700
Data Index: 3278393 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5451. Min Range: -6.5451
Max Act: 5.8889. Min Act: -0.1700
Data Index: 7572554 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #19