Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3239 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9252. Min Range: -6.9252
Max Act: 6.9252. Min Act: -0.1700
Data Index: 2543127 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9252. Min Range: -6.9252
Max Act: 6.3939. Min Act: -0.1700
Data Index: 4533783 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9252. Min Range: -6.9252
Max Act: 6.3939. Min Act: -0.1700
Data Index: 4533781 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9252. Min Range: -6.9252
Max Act: 6.3002. Min Act: -0.1700
Data Index: 2543126 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9252. Min Range: -6.9252
Max Act: 6.2689. Min Act: -0.1700
Data Index: 6721253 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9252. Min Range: -6.9252
Max Act: 6.2377. Min Act: -0.1700
Data Index: 8065126 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9252. Min Range: -6.9252
Max Act: 6.1752. Min Act: -0.1700
Data Index: 1068088 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9252. Min Range: -6.9252
Max Act: 6.1127. Min Act: -0.1700
Data Index: 7653628 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9252. Min Range: -6.9252
Max Act: 6.1127. Min Act: -0.1700
Data Index: 6386270 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9252. Min Range: -6.9252
Max Act: 6.1439. Min Act: -0.1700
Data Index: 970301 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9252. Min Range: -6.9252
Max Act: 6.1127. Min Act: -0.1700
Data Index: 6520659 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9252. Min Range: -6.9252
Max Act: 6.0814. Min Act: -0.1700
Data Index: 280399 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9252. Min Range: -6.9252
Max Act: 6.0502. Min Act: -0.1700
Data Index: 4703456 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9252. Min Range: -6.9252
Max Act: 5.9877. Min Act: -0.1700
Data Index: 2872790 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9252. Min Range: -6.9252
Max Act: 5.9564. Min Act: -0.1700
Data Index: 1070135 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9252. Min Range: -6.9252
Max Act: 5.9564. Min Act: -0.1700
Data Index: 5815105 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9252. Min Range: -6.9252
Max Act: 5.9564. Min Act: -0.1700
Data Index: 493961 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9252. Min Range: -6.9252
Max Act: 5.9252. Min Act: -0.1700
Data Index: 3314854 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9252. Min Range: -6.9252
Max Act: 5.9564. Min Act: -0.1700
Data Index: 5760988 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9252. Min Range: -6.9252
Max Act: 5.9252. Min Act: -0.1700
Data Index: 1060230 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19