Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 828 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4162. Min Range: -6.4162
Max Act: 6.4162. Min Act: -0.1700
Data Index: 2660583 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4162. Min Range: -6.4162
Max Act: 6.2287. Min Act: -0.1700
Data Index: 6953594 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4162. Min Range: -6.4162
Max Act: 6.1349. Min Act: -0.1700
Data Index: 8456681 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4162. Min Range: -6.4162
Max Act: 6.0724. Min Act: -0.1700
Data Index: 239104 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4162. Min Range: -6.4162
Max Act: 6.0724. Min Act: -0.1700
Data Index: 6912251 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4162. Min Range: -6.4162
Max Act: 6.0099. Min Act: -0.1700
Data Index: 1020857 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4162. Min Range: -6.4162
Max Act: 5.9787. Min Act: -0.1700
Data Index: 8456682 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4162. Min Range: -6.4162
Max Act: 5.8849. Min Act: -0.1700
Data Index: 3334449 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4162. Min Range: -6.4162
Max Act: 5.8849. Min Act: -0.1700
Data Index: 8151167 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4162. Min Range: -6.4162
Max Act: 5.8537. Min Act: -0.1700
Data Index: 996171 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4162. Min Range: -6.4162
Max Act: 5.8224. Min Act: -0.1700
Data Index: 5537977 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4162. Min Range: -6.4162
Max Act: 5.8224. Min Act: -0.1700
Data Index: 8114576 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4162. Min Range: -6.4162
Max Act: 5.8224. Min Act: -0.1700
Data Index: 3192331 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4162. Min Range: -6.4162
Max Act: 5.7912. Min Act: -0.1700
Data Index: 6433491 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4162. Min Range: -6.4162
Max Act: 5.8537. Min Act: -0.1700
Data Index: 3712971 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4162. Min Range: -6.4162
Max Act: 5.7912. Min Act: -0.1700
Data Index: 5521681 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4162. Min Range: -6.4162
Max Act: 5.7912. Min Act: -0.1700
Data Index: 1518693 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4162. Min Range: -6.4162
Max Act: 5.7912. Min Act: -0.1700
Data Index: 6936572 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4162. Min Range: -6.4162
Max Act: 5.7912. Min Act: -0.1700
Data Index: 3824320 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4162. Min Range: -6.4162
Max Act: 5.7912. Min Act: -0.1700
Data Index: 8012966 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19