Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5843 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.7543. Min Range: -10.7543
Max Act: 10.7543. Min Act: -0.1700
Data Index: 8648247 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7543. Min Range: -10.7543
Max Act: 9.8793. Min Act: -0.1700
Data Index: 3045844 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7543. Min Range: -10.7543
Max Act: 9.7543. Min Act: -0.1700
Data Index: 672287 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7543. Min Range: -10.7543
Max Act: 9.6293. Min Act: -0.1700
Data Index: 1466643 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7543. Min Range: -10.7543
Max Act: 9.4418. Min Act: -0.1698
Data Index: 3958089 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7543. Min Range: -10.7543
Max Act: 9.5043. Min Act: -0.1700
Data Index: 4633410 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7543. Min Range: -10.7543
Max Act: 9.3793. Min Act: -0.1700
Data Index: 7974370 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7543. Min Range: -10.7543
Max Act: 9.3793. Min Act: -0.1700
Data Index: 6324345 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7543. Min Range: -10.7543
Max Act: 9.3793. Min Act: -0.1700
Data Index: 6324343 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7543. Min Range: -10.7543
Max Act: 9.3168. Min Act: -0.1700
Data Index: 3907655 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7543. Min Range: -10.7543
Max Act: 9.1918. Min Act: -0.1700
Data Index: 6986559 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7543. Min Range: -10.7543
Max Act: 9.1918. Min Act: -0.1700
Data Index: 7378381 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7543. Min Range: -10.7543
Max Act: 9.1293. Min Act: -0.1700
Data Index: 2075951 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7543. Min Range: -10.7543
Max Act: 9.1918. Min Act: -0.1700
Data Index: 6241391 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7543. Min Range: -10.7543
Max Act: 9.1918. Min Act: -0.1700
Data Index: 6013813 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7543. Min Range: -10.7543
Max Act: 9.2543. Min Act: -0.1700
Data Index: 8694528 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7543. Min Range: -10.7543
Max Act: 9.1293. Min Act: -0.1700
Data Index: 58028 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7543. Min Range: -10.7543
Max Act: 9.1293. Min Act: -0.1700
Data Index: 7835053 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7543. Min Range: -10.7543
Max Act: 9.1293. Min Act: -0.1700
Data Index: 2540675 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7543. Min Range: -10.7543
Max Act: 9.0668. Min Act: -0.1700
Data Index: 4737124 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19