Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 226 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.7796. Min Range: -9.7796
Max Act: 9.7796. Min Act: -0.1700
Data Index: 7525265 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7796. Min Range: -9.7796
Max Act: 9.5296. Min Act: -0.1700
Data Index: 320860 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7796. Min Range: -9.7796
Max Act: 9.5296. Min Act: -0.1700
Data Index: 8539620 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7796. Min Range: -9.7796
Max Act: 9.5921. Min Act: -0.1700
Data Index: 3868073 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7796. Min Range: -9.7796
Max Act: 9.4671. Min Act: -0.1700
Data Index: 2229885 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7796. Min Range: -9.7796
Max Act: 9.4046. Min Act: -0.1700
Data Index: 7906010 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7796. Min Range: -9.7796
Max Act: 9.4671. Min Act: -0.1700
Data Index: 3904524 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7796. Min Range: -9.7796
Max Act: 9.4671. Min Act: -0.1700
Data Index: 1620868 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7796. Min Range: -9.7796
Max Act: 9.4046. Min Act: -0.1700
Data Index: 2132553 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7796. Min Range: -9.7796
Max Act: 9.2796. Min Act: -0.1700
Data Index: 8798526 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7796. Min Range: -9.7796
Max Act: 9.2796. Min Act: -0.1700
Data Index: 3686252 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7796. Min Range: -9.7796
Max Act: 9.2171. Min Act: -0.1700
Data Index: 6885228 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7796. Min Range: -9.7796
Max Act: 9.2796. Min Act: -0.1700
Data Index: 5344306 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7796. Min Range: -9.7796
Max Act: 9.2796. Min Act: -0.1700
Data Index: 5305416 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7796. Min Range: -9.7796
Max Act: 9.2796. Min Act: -0.1700
Data Index: 6459120 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7796. Min Range: -9.7796
Max Act: 9.2171. Min Act: -0.1700
Data Index: 5424666 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7796. Min Range: -9.7796
Max Act: 9.2796. Min Act: -0.1700
Data Index: 6739853 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7796. Min Range: -9.7796
Max Act: 9.2171. Min Act: -0.1700
Data Index: 8065988 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7796. Min Range: -9.7796
Max Act: 9.2171. Min Act: -0.1700
Data Index: 8454150 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7796. Min Range: -9.7796
Max Act: 9.2171. Min Act: -0.1700
Data Index: 6418514 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19