Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 224 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6588. Min Range: -8.6588
Max Act: 8.6588. Min Act: -0.1700
Data Index: 1304341 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6588. Min Range: -8.6588
Max Act: 8.4713. Min Act: -0.1700
Data Index: 8470823 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6588. Min Range: -8.6588
Max Act: 8.3463. Min Act: -0.1700
Data Index: 7778986 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6588. Min Range: -8.6588
Max Act: 8.1588. Min Act: -0.1700
Data Index: 4694130 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6588. Min Range: -8.6588
Max Act: 8.1588. Min Act: -0.1700
Data Index: 7778987 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6588. Min Range: -8.6588
Max Act: 8.1588. Min Act: -0.1700
Data Index: 727126 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6588. Min Range: -8.6588
Max Act: 8.0963. Min Act: -0.1700
Data Index: 8506617 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6588. Min Range: -8.6588
Max Act: 8.0963. Min Act: -0.1700
Data Index: 1941454 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6588. Min Range: -8.6588
Max Act: 8.0963. Min Act: -0.1700
Data Index: 719134 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6588. Min Range: -8.6588
Max Act: 7.9713. Min Act: -0.1700
Data Index: 1998041 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6588. Min Range: -8.6588
Max Act: 8.0963. Min Act: -0.1700
Data Index: 7540843 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6588. Min Range: -8.6588
Max Act: 8.0338. Min Act: -0.1700
Data Index: 6921198 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6588. Min Range: -8.6588
Max Act: 7.9713. Min Act: -0.1700
Data Index: 1941457 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6588. Min Range: -8.6588
Max Act: 7.9713. Min Act: -0.1700
Data Index: 7990485 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6588. Min Range: -8.6588
Max Act: 7.9713. Min Act: -0.1700
Data Index: 7449033 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6588. Min Range: -8.6588
Max Act: 7.9713. Min Act: -0.1700
Data Index: 4279970 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6588. Min Range: -8.6588
Max Act: 7.9713. Min Act: -0.1700
Data Index: 1021729 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6588. Min Range: -8.6588
Max Act: 7.9088. Min Act: -0.1700
Data Index: 1277204 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6588. Min Range: -8.6588
Max Act: 7.9088. Min Act: -0.1700
Data Index: 5275571 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6588. Min Range: -8.6588
Max Act: 7.9088. Min Act: -0.1700
Data Index: 4844275 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19