Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2627 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4588. Min Range: -7.4588
Max Act: 7.4588. Min Act: -0.1700
Data Index: 5383243 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4588. Min Range: -7.4588
Max Act: 7.4276. Min Act: -0.1700
Data Index: 2759300 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4588. Min Range: -7.4588
Max Act: 7.3963. Min Act: -0.1700
Data Index: 4893784 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4588. Min Range: -7.4588
Max Act: 7.2713. Min Act: -0.1700
Data Index: 5885961 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4588. Min Range: -7.4588
Max Act: 7.1776. Min Act: -0.1700
Data Index: 7684799 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4588. Min Range: -7.4588
Max Act: 7.1463. Min Act: -0.1700
Data Index: 796108 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4588. Min Range: -7.4588
Max Act: 7.1463. Min Act: -0.1700
Data Index: 6607022 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4588. Min Range: -7.4588
Max Act: 7.1151. Min Act: -0.1700
Data Index: 341752 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4588. Min Range: -7.4588
Max Act: 7.1151. Min Act: -0.1700
Data Index: 4122035 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4588. Min Range: -7.4588
Max Act: 7.0526. Min Act: -0.1700
Data Index: 401162 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4588. Min Range: -7.4588
Max Act: 7.0213. Min Act: -0.1700
Data Index: 8257315 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4588. Min Range: -7.4588
Max Act: 6.9901. Min Act: -0.1700
Data Index: 3286157 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4588. Min Range: -7.4588
Max Act: 6.9901. Min Act: -0.1700
Data Index: 652274 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4588. Min Range: -7.4588
Max Act: 6.9588. Min Act: -0.1700
Data Index: 3569295 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4588. Min Range: -7.4588
Max Act: 6.9588. Min Act: -0.1700
Data Index: 2200012 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4588. Min Range: -7.4588
Max Act: 6.9588. Min Act: -0.1700
Data Index: 5806328 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4588. Min Range: -7.4588
Max Act: 6.9276. Min Act: -0.1700
Data Index: 3160570 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4588. Min Range: -7.4588
Max Act: 6.9276. Min Act: -0.1700
Data Index: 3769666 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4588. Min Range: -7.4588
Max Act: 6.8963. Min Act: -0.1700
Data Index: 7553777 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4588. Min Range: -7.4588
Max Act: 6.8963. Min Act: -0.1700
Data Index: 4323620 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #19