Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3431 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1498. Min Range: -5.1498
Max Act: 5.1498. Min Act: -0.1700
Data Index: 7660910 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1498. Min Range: -5.1498
Max Act: 5.0873. Min Act: -0.1700
Data Index: 434501 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1498. Min Range: -5.1498
Max Act: 4.8685. Min Act: -0.1700
Data Index: 5063310 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1498. Min Range: -5.1498
Max Act: 4.7748. Min Act: -0.1700
Data Index: 4640123 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1498. Min Range: -5.1498
Max Act: 4.7748. Min Act: -0.1700
Data Index: 5766822 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1498. Min Range: -5.1498
Max Act: 4.7748. Min Act: -0.1700
Data Index: 5526483 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1498. Min Range: -5.1498
Max Act: 4.7748. Min Act: -0.1700
Data Index: 3880847 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1498. Min Range: -5.1498
Max Act: 4.7748. Min Act: -0.1700
Data Index: 1093628 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1498. Min Range: -5.1498
Max Act: 4.7123. Min Act: -0.1700
Data Index: 6610297 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1498. Min Range: -5.1498
Max Act: 4.7435. Min Act: -0.1700
Data Index: 5979769 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1498. Min Range: -5.1498
Max Act: 4.7435. Min Act: -0.1700
Data Index: 3182707 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1498. Min Range: -5.1498
Max Act: 4.7123. Min Act: -0.1700
Data Index: 2394134 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1498. Min Range: -5.1498
Max Act: 4.7123. Min Act: -0.1700
Data Index: 8254187 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1498. Min Range: -5.1498
Max Act: 4.7123. Min Act: -0.1700
Data Index: 8579909 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1498. Min Range: -5.1498
Max Act: 4.7123. Min Act: -0.1700
Data Index: 7501229 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1498. Min Range: -5.1498
Max Act: 4.7123. Min Act: -0.1700
Data Index: 1594405 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1498. Min Range: -5.1498
Max Act: 4.6810. Min Act: -0.1700
Data Index: 5243927 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1498. Min Range: -5.1498
Max Act: 4.7123. Min Act: -0.1700
Data Index: 2809502 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1498. Min Range: -5.1498
Max Act: 4.7123. Min Act: -0.1700
Data Index: 329140 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1498. Min Range: -5.1498
Max Act: 4.6810. Min Act: -0.1700
Data Index: 105630 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19