Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2043 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7628. Min Range: -5.7628
Max Act: 5.7628. Min Act: -0.1700
Data Index: 880491 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7628. Min Range: -5.7628
Max Act: 5.2315. Min Act: -0.1700
Data Index: 5613683 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7628. Min Range: -5.7628
Max Act: 5.1690. Min Act: -0.1700
Data Index: 2847920 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7628. Min Range: -5.7628
Max Act: 5.1690. Min Act: -0.1700
Data Index: 4477701 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7628. Min Range: -5.7628
Max Act: 5.1378. Min Act: -0.1700
Data Index: 1764796 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7628. Min Range: -5.7628
Max Act: 5.1065. Min Act: -0.1700
Data Index: 2786504 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7628. Min Range: -5.7628
Max Act: 5.1065. Min Act: -0.1700
Data Index: 866061 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7628. Min Range: -5.7628
Max Act: 5.1065. Min Act: -0.1700
Data Index: 2847933 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7628. Min Range: -5.7628
Max Act: 5.1065. Min Act: -0.1700
Data Index: 2847924 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7628. Min Range: -5.7628
Max Act: 5.1378. Min Act: -0.1700
Data Index: 4477722 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7628. Min Range: -5.7628
Max Act: 5.0753. Min Act: -0.1700
Data Index: 7339398 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7628. Min Range: -5.7628
Max Act: 5.0128. Min Act: -0.1700
Data Index: 2260784 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7628. Min Range: -5.7628
Max Act: 4.9815. Min Act: -0.1700
Data Index: 1163623 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7628. Min Range: -5.7628
Max Act: 5.0128. Min Act: -0.1700
Data Index: 497893 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7628. Min Range: -5.7628
Max Act: 5.0128. Min Act: -0.1700
Data Index: 1682148 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7628. Min Range: -5.7628
Max Act: 4.9503. Min Act: -0.1700
Data Index: 144055 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7628. Min Range: -5.7628
Max Act: 4.9190. Min Act: -0.1700
Data Index: 1547228 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7628. Min Range: -5.7628
Max Act: 4.8878. Min Act: -0.1700
Data Index: 5263265 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7628. Min Range: -5.7628
Max Act: 4.9503. Min Act: -0.1700
Data Index: 118210 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7628. Min Range: -5.7628
Max Act: 4.9190. Min Act: -0.1700
Data Index: 3500194 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19