Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2567 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.2465. Min Range: -8.2465
Max Act: 8.2465. Min Act: -0.1700
Data Index: 6824194 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2465. Min Range: -8.2465
Max Act: 8.2465. Min Act: -0.1700
Data Index: 42815 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2465. Min Range: -8.2465
Max Act: 8.1840. Min Act: -0.1700
Data Index: 4678614 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2465. Min Range: -8.2465
Max Act: 8.1840. Min Act: -0.1700
Data Index: 2306522 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2465. Min Range: -8.2465
Max Act: 8.1215. Min Act: -0.1700
Data Index: 8669723 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2465. Min Range: -8.2465
Max Act: 7.9965. Min Act: -0.1700
Data Index: 4687235 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2465. Min Range: -8.2465
Max Act: 7.9652. Min Act: -0.1700
Data Index: 3817399 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2465. Min Range: -8.2465
Max Act: 7.9340. Min Act: -0.1700
Data Index: 4551542 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2465. Min Range: -8.2465
Max Act: 7.8402. Min Act: -0.1700
Data Index: 7979535 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2465. Min Range: -8.2465
Max Act: 7.8402. Min Act: -0.1700
Data Index: 4748628 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2465. Min Range: -8.2465
Max Act: 7.8402. Min Act: -0.1700
Data Index: 6872049 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2465. Min Range: -8.2465
Max Act: 7.8402. Min Act: -0.1700
Data Index: 849122 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2465. Min Range: -8.2465
Max Act: 7.7777. Min Act: -0.1700
Data Index: 1065941 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2465. Min Range: -8.2465
Max Act: 7.7465. Min Act: -0.1700
Data Index: 2918381 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2465. Min Range: -8.2465
Max Act: 7.7465. Min Act: -0.1700
Data Index: 8495211 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2465. Min Range: -8.2465
Max Act: 7.6840. Min Act: -0.1700
Data Index: 8271018 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2465. Min Range: -8.2465
Max Act: 7.6527. Min Act: -0.1700
Data Index: 3939696 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2465. Min Range: -8.2465
Max Act: 7.7152. Min Act: -0.1700
Data Index: 5316930 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2465. Min Range: -8.2465
Max Act: 7.6840. Min Act: -0.1700
Data Index: 1730853 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2465. Min Range: -8.2465
Max Act: 7.6527. Min Act: -0.1700
Data Index: 5102518 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #19