Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3411 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3980. Min Range: -6.3980
Max Act: 6.3980. Min Act: -0.1700
Data Index: 5787049 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3980. Min Range: -6.3980
Max Act: 6.2418. Min Act: -0.1700
Data Index: 1277275 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3980. Min Range: -6.3980
Max Act: 6.1168. Min Act: -0.1700
Data Index: 5882458 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3980. Min Range: -6.3980
Max Act: 6.0855. Min Act: -0.1700
Data Index: 4749594 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3980. Min Range: -6.3980
Max Act: 6.1168. Min Act: -0.1700
Data Index: 5209760 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3980. Min Range: -6.3980
Max Act: 6.0855. Min Act: -0.1700
Data Index: 735489 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3980. Min Range: -6.3980
Max Act: 6.0855. Min Act: -0.1700
Data Index: 8709788 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3980. Min Range: -6.3980
Max Act: 6.0543. Min Act: -0.1700
Data Index: 1906654 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3980. Min Range: -6.3980
Max Act: 6.0230. Min Act: -0.1700
Data Index: 365108 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3980. Min Range: -6.3980
Max Act: 6.0230. Min Act: -0.1700
Data Index: 5557172 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3980. Min Range: -6.3980
Max Act: 5.9918. Min Act: -0.1700
Data Index: 3110107 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3980. Min Range: -6.3980
Max Act: 5.9605. Min Act: -0.1700
Data Index: 6180390 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3980. Min Range: -6.3980
Max Act: 5.9605. Min Act: -0.1700
Data Index: 699814 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3980. Min Range: -6.3980
Max Act: 5.9605. Min Act: -0.1700
Data Index: 4901143 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3980. Min Range: -6.3980
Max Act: 5.8980. Min Act: -0.1700
Data Index: 3170455 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3980. Min Range: -6.3980
Max Act: 5.8355. Min Act: -0.1700
Data Index: 4064397 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3980. Min Range: -6.3980
Max Act: 5.8668. Min Act: -0.1700
Data Index: 3573726 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3980. Min Range: -6.3980
Max Act: 5.8668. Min Act: -0.1700
Data Index: 2038934 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3980. Min Range: -6.3980
Max Act: 5.8668. Min Act: -0.1700
Data Index: 1220561 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3980. Min Range: -6.3980
Max Act: 5.8355. Min Act: -0.1700
Data Index: 1925501 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #19