Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1567 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6317. Min Range: -6.6317
Max Act: 6.6317. Min Act: -0.1700
Data Index: 3064557 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6317. Min Range: -6.6317
Max Act: 6.5067. Min Act: -0.1700
Data Index: 2431464 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6317. Min Range: -6.6317
Max Act: 6.4754. Min Act: -0.1700
Data Index: 8372478 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6317. Min Range: -6.6317
Max Act: 6.4754. Min Act: -0.1700
Data Index: 5069023 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6317. Min Range: -6.6317
Max Act: 6.4754. Min Act: -0.1700
Data Index: 1774360 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6317. Min Range: -6.6317
Max Act: 6.4754. Min Act: -0.1700
Data Index: 7129243 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6317. Min Range: -6.6317
Max Act: 6.4442. Min Act: -0.1700
Data Index: 8154059 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6317. Min Range: -6.6317
Max Act: 6.4442. Min Act: -0.1700
Data Index: 2852230 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6317. Min Range: -6.6317
Max Act: 6.4442. Min Act: -0.1700
Data Index: 4139193 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6317. Min Range: -6.6317
Max Act: 6.4442. Min Act: -0.1700
Data Index: 4137704 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6317. Min Range: -6.6317
Max Act: 6.4442. Min Act: -0.1700
Data Index: 3483196 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6317. Min Range: -6.6317
Max Act: 6.4129. Min Act: -0.1700
Data Index: 7121952 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6317. Min Range: -6.6317
Max Act: 6.3817. Min Act: -0.1700
Data Index: 552657 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6317. Min Range: -6.6317
Max Act: 6.3817. Min Act: -0.1700
Data Index: 4114768 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6317. Min Range: -6.6317
Max Act: 6.3817. Min Act: -0.1700
Data Index: 480401 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6317. Min Range: -6.6317
Max Act: 6.3817. Min Act: -0.1700
Data Index: 6105246 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6317. Min Range: -6.6317
Max Act: 6.3504. Min Act: -0.1700
Data Index: 5963293 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6317. Min Range: -6.6317
Max Act: 6.3504. Min Act: -0.1700
Data Index: 2066333 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6317. Min Range: -6.6317
Max Act: 6.3817. Min Act: -0.1700
Data Index: 5481566 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6317. Min Range: -6.6317
Max Act: 6.3817. Min Act: -0.1700
Data Index: 1868663 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19