Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5201 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4195. Min Range: -6.4195
Max Act: 6.4195. Min Act: -0.1700
Data Index: 8553362 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4195. Min Range: -6.4195
Max Act: 6.1383. Min Act: -0.1700
Data Index: 6944664 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4195. Min Range: -6.4195
Max Act: 6.0758. Min Act: -0.1700
Data Index: 7251858 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4195. Min Range: -6.4195
Max Act: 5.9195. Min Act: -0.1700
Data Index: 2170013 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4195. Min Range: -6.4195
Max Act: 5.8883. Min Act: -0.1700
Data Index: 3313125 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4195. Min Range: -6.4195
Max Act: 5.8258. Min Act: -0.1700
Data Index: 2890210 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4195. Min Range: -6.4195
Max Act: 5.8258. Min Act: -0.1700
Data Index: 1994402 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4195. Min Range: -6.4195
Max Act: 5.7945. Min Act: -0.1700
Data Index: 5839446 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4195. Min Range: -6.4195
Max Act: 5.7945. Min Act: -0.1700
Data Index: 5163844 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4195. Min Range: -6.4195
Max Act: 5.7633. Min Act: -0.1700
Data Index: 5678234 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4195. Min Range: -6.4195
Max Act: 5.7008. Min Act: -0.1700
Data Index: 5786600 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4195. Min Range: -6.4195
Max Act: 5.6695. Min Act: -0.1700
Data Index: 8630590 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4195. Min Range: -6.4195
Max Act: 5.7008. Min Act: -0.1700
Data Index: 4358407 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4195. Min Range: -6.4195
Max Act: 5.7320. Min Act: -0.1700
Data Index: 211476 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4195. Min Range: -6.4195
Max Act: 5.7008. Min Act: -0.1700
Data Index: 3691360 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4195. Min Range: -6.4195
Max Act: 5.7008. Min Act: -0.1700
Data Index: 2924136 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4195. Min Range: -6.4195
Max Act: 5.6383. Min Act: -0.1700
Data Index: 366977 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4195. Min Range: -6.4195
Max Act: 5.6695. Min Act: -0.1700
Data Index: 5804567 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4195. Min Range: -6.4195
Max Act: 5.6695. Min Act: -0.1700
Data Index: 1203604 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4195. Min Range: -6.4195
Max Act: 5.6383. Min Act: -0.1700
Data Index: 3779923 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19