Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2055 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.7215. Min Range: -8.7215
Max Act: 8.7215. Min Act: -0.1700
Data Index: 1562689 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7215. Min Range: -8.7215
Max Act: 8.5965. Min Act: -0.1700
Data Index: 4416499 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7215. Min Range: -8.7215
Max Act: 8.5340. Min Act: -0.1700
Data Index: 1102595 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7215. Min Range: -8.7215
Max Act: 8.4090. Min Act: -0.1700
Data Index: 2623488 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7215. Min Range: -8.7215
Max Act: 8.3465. Min Act: -0.1700
Data Index: 6943638 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7215. Min Range: -8.7215
Max Act: 8.2840. Min Act: -0.1700
Data Index: 8718547 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7215. Min Range: -8.7215
Max Act: 8.2215. Min Act: -0.1700
Data Index: 7066010 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7215. Min Range: -8.7215
Max Act: 8.1590. Min Act: -0.1700
Data Index: 955121 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7215. Min Range: -8.7215
Max Act: 8.1590. Min Act: -0.1700
Data Index: 4191149 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7215. Min Range: -8.7215
Max Act: 8.1590. Min Act: -0.1700
Data Index: 5494133 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7215. Min Range: -8.7215
Max Act: 8.0340. Min Act: -0.1700
Data Index: 62163 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7215. Min Range: -8.7215
Max Act: 8.0965. Min Act: -0.1700
Data Index: 5438202 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7215. Min Range: -8.7215
Max Act: 8.1590. Min Act: -0.1700
Data Index: 7822738 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7215. Min Range: -8.7215
Max Act: 8.0340. Min Act: -0.1700
Data Index: 3914377 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7215. Min Range: -8.7215
Max Act: 8.0340. Min Act: -0.1700
Data Index: 8340475 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7215. Min Range: -8.7215
Max Act: 8.0340. Min Act: -0.1700
Data Index: 4181771 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7215. Min Range: -8.7215
Max Act: 8.0340. Min Act: -0.1700
Data Index: 474811 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7215. Min Range: -8.7215
Max Act: 7.9715. Min Act: -0.1700
Data Index: 1263605 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7215. Min Range: -8.7215
Max Act: 7.9715. Min Act: -0.1700
Data Index: 1856340 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7215. Min Range: -8.7215
Max Act: 7.9715. Min Act: -0.1700
Data Index: 3484725 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19