Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5274 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0188. Min Range: -6.0188
Max Act: 6.0188. Min Act: -0.1700
Data Index: 7283329 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0188. Min Range: -6.0188
Max Act: 5.9875. Min Act: -0.1700
Data Index: 3319726 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0188. Min Range: -6.0188
Max Act: 5.8313. Min Act: -0.1700
Data Index: 4837775 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0188. Min Range: -6.0188
Max Act: 5.8000. Min Act: -0.1700
Data Index: 3223936 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0188. Min Range: -6.0188
Max Act: 5.7688. Min Act: -0.1700
Data Index: 6044416 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0188. Min Range: -6.0188
Max Act: 5.7375. Min Act: -0.1700
Data Index: 4847120 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0188. Min Range: -6.0188
Max Act: 5.7375. Min Act: -0.1700
Data Index: 2630402 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0188. Min Range: -6.0188
Max Act: 5.6438. Min Act: -0.1700
Data Index: 2083784 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0188. Min Range: -6.0188
Max Act: 5.5813. Min Act: -0.1700
Data Index: 2950082 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0188. Min Range: -6.0188
Max Act: 5.6125. Min Act: -0.1700
Data Index: 6131331 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0188. Min Range: -6.0188
Max Act: 5.6125. Min Act: -0.1700
Data Index: 1125099 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0188. Min Range: -6.0188
Max Act: 5.6125. Min Act: -0.1700
Data Index: 4764008 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0188. Min Range: -6.0188
Max Act: 5.5813. Min Act: -0.1700
Data Index: 7217906 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0188. Min Range: -6.0188
Max Act: 5.5813. Min Act: -0.1700
Data Index: 3222148 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0188. Min Range: -6.0188
Max Act: 5.5500. Min Act: -0.1700
Data Index: 6603808 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0188. Min Range: -6.0188
Max Act: 5.5500. Min Act: -0.1700
Data Index: 5799201 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0188. Min Range: -6.0188
Max Act: 5.5188. Min Act: -0.1700
Data Index: 4453531 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0188. Min Range: -6.0188
Max Act: 5.4875. Min Act: -0.1700
Data Index: 6172428 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0188. Min Range: -6.0188
Max Act: 5.4875. Min Act: -0.1700
Data Index: 389304 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0188. Min Range: -6.0188
Max Act: 5.4875. Min Act: -0.1700
Data Index: 297971 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19