Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2398 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0616. Min Range: -7.0616
Max Act: 7.0616. Min Act: -0.1700
Data Index: 22740 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0616. Min Range: -7.0616
Max Act: 7.0303. Min Act: -0.1700
Data Index: 6502690 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0616. Min Range: -7.0616
Max Act: 6.9678. Min Act: -0.1700
Data Index: 6859897 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0616. Min Range: -7.0616
Max Act: 6.9366. Min Act: -0.1700
Data Index: 658463 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0616. Min Range: -7.0616
Max Act: 6.9053. Min Act: -0.1700
Data Index: 4369036 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0616. Min Range: -7.0616
Max Act: 6.9053. Min Act: -0.1700
Data Index: 1301049 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0616. Min Range: -7.0616
Max Act: 6.9053. Min Act: -0.1700
Data Index: 2555295 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0616. Min Range: -7.0616
Max Act: 6.8741. Min Act: -0.1700
Data Index: 4373309 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0616. Min Range: -7.0616
Max Act: 6.8741. Min Act: -0.1700
Data Index: 5532483 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0616. Min Range: -7.0616
Max Act: 6.7803. Min Act: -0.1700
Data Index: 8566048 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0616. Min Range: -7.0616
Max Act: 6.7491. Min Act: -0.1700
Data Index: 7026985 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0616. Min Range: -7.0616
Max Act: 6.7178. Min Act: -0.1700
Data Index: 4947428 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0616. Min Range: -7.0616
Max Act: 6.6866. Min Act: -0.1700
Data Index: 3341054 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0616. Min Range: -7.0616
Max Act: 6.6866. Min Act: -0.1700
Data Index: 7751111 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0616. Min Range: -7.0616
Max Act: 6.6866. Min Act: -0.1700
Data Index: 5491097 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0616. Min Range: -7.0616
Max Act: 6.6241. Min Act: -0.1700
Data Index: 8818870 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0616. Min Range: -7.0616
Max Act: 6.6241. Min Act: -0.1700
Data Index: 1270034 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0616. Min Range: -7.0616
Max Act: 6.5928. Min Act: -0.1700
Data Index: 3608091 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0616. Min Range: -7.0616
Max Act: 6.5928. Min Act: -0.1700
Data Index: 6124766 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0616. Min Range: -7.0616
Max Act: 6.5616. Min Act: -0.1700
Data Index: 4936708 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #19