Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1091 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.6057. Min Range: -7.6057
Max Act: 7.6057. Min Act: -0.1700
Data Index: 4172462 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6057. Min Range: -7.6057
Max Act: 7.4494. Min Act: -0.1700
Data Index: 7179474 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6057. Min Range: -7.6057
Max Act: 7.4182. Min Act: -0.1700
Data Index: 4253211 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6057. Min Range: -7.6057
Max Act: 7.3869. Min Act: -0.1700
Data Index: 617407 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6057. Min Range: -7.6057
Max Act: 7.3869. Min Act: -0.1700
Data Index: 5032909 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6057. Min Range: -7.6057
Max Act: 7.3869. Min Act: -0.1700
Data Index: 5416876 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6057. Min Range: -7.6057
Max Act: 7.3244. Min Act: -0.1700
Data Index: 383527 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6057. Min Range: -7.6057
Max Act: 7.3557. Min Act: -0.1700
Data Index: 6298798 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6057. Min Range: -7.6057
Max Act: 7.3557. Min Act: -0.1700
Data Index: 573295 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6057. Min Range: -7.6057
Max Act: 7.3557. Min Act: -0.1700
Data Index: 3936051 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6057. Min Range: -7.6057
Max Act: 7.3557. Min Act: -0.1700
Data Index: 8705812 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6057. Min Range: -7.6057
Max Act: 7.3244. Min Act: -0.1700
Data Index: 7490524 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6057. Min Range: -7.6057
Max Act: 7.3557. Min Act: -0.1700
Data Index: 1027390 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6057. Min Range: -7.6057
Max Act: 7.2932. Min Act: -0.1700
Data Index: 1461382 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6057. Min Range: -7.6057
Max Act: 7.3557. Min Act: -0.1700
Data Index: 1476860 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6057. Min Range: -7.6057
Max Act: 7.3244. Min Act: -0.1700
Data Index: 1250080 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6057. Min Range: -7.6057
Max Act: 7.2932. Min Act: -0.1700
Data Index: 6184352 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6057. Min Range: -7.6057
Max Act: 7.3557. Min Act: -0.1700
Data Index: 4210019 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6057. Min Range: -7.6057
Max Act: 7.3557. Min Act: -0.1700
Data Index: 4747974 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6057. Min Range: -7.6057
Max Act: 7.2932. Min Act: -0.1700
Data Index: 6643765 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19