Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5105 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6588. Min Range: -6.6588
Max Act: 6.6588. Min Act: -0.1700
Data Index: 4083729 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6588. Min Range: -6.6588
Max Act: 6.3775. Min Act: -0.1700
Data Index: 5529809 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6588. Min Range: -6.6588
Max Act: 6.3775. Min Act: -0.1700
Data Index: 6214697 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6588. Min Range: -6.6588
Max Act: 6.4088. Min Act: -0.1700
Data Index: 3683873 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6588. Min Range: -6.6588
Max Act: 6.3463. Min Act: -0.1700
Data Index: 7948062 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6588. Min Range: -6.6588
Max Act: 6.3150. Min Act: -0.1700
Data Index: 1667477 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6588. Min Range: -6.6588
Max Act: 6.3150. Min Act: -0.1700
Data Index: 4083736 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6588. Min Range: -6.6588
Max Act: 6.3150. Min Act: -0.1700
Data Index: 4599288 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6588. Min Range: -6.6588
Max Act: 6.2525. Min Act: -0.1700
Data Index: 7514172 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6588. Min Range: -6.6588
Max Act: 6.2213. Min Act: -0.1700
Data Index: 1073056 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6588. Min Range: -6.6588
Max Act: 6.2213. Min Act: -0.1700
Data Index: 2946339 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6588. Min Range: -6.6588
Max Act: 6.2213. Min Act: -0.1700
Data Index: 4559130 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6588. Min Range: -6.6588
Max Act: 6.1900. Min Act: -0.1700
Data Index: 4554125 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6588. Min Range: -6.6588
Max Act: 6.1588. Min Act: -0.1700
Data Index: 4455626 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6588. Min Range: -6.6588
Max Act: 6.0963. Min Act: -0.1700
Data Index: 97272 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6588. Min Range: -6.6588
Max Act: 6.0963. Min Act: -0.1700
Data Index: 447210 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6588. Min Range: -6.6588
Max Act: 6.0650. Min Act: -0.1700
Data Index: 7300649 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6588. Min Range: -6.6588
Max Act: 6.0963. Min Act: -0.1700
Data Index: 8204114 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6588. Min Range: -6.6588
Max Act: 6.0650. Min Act: -0.1700
Data Index: 5082043 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6588. Min Range: -6.6588
Max Act: 6.0963. Min Act: -0.1700
Data Index: 136382 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19