Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3108 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4518. Min Range: -3.4518
Max Act: 3.4048. Min Act: -0.1700
Data Index: 8437184 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4518. Min Range: -3.4518
Max Act: 3.4518. Min Act: -0.1700
Data Index: 1456524 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4518. Min Range: -3.4518
Max Act: 3.4362. Min Act: -0.1700
Data Index: 7182778 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4518. Min Range: -3.4518
Max Act: 3.4362. Min Act: -0.1700
Data Index: 2209120 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4518. Min Range: -3.4518
Max Act: 3.4048. Min Act: -0.1700
Data Index: 6424207 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4518. Min Range: -3.4518
Max Act: 3.4205. Min Act: -0.1700
Data Index: 4999460 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4518. Min Range: -3.4518
Max Act: 3.3421. Min Act: -0.1700
Data Index: 573704 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4518. Min Range: -3.4518
Max Act: 3.2793. Min Act: -0.1700
Data Index: 100898 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4518. Min Range: -3.4518
Max Act: 3.2636. Min Act: -0.1700
Data Index: 4433740 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4518. Min Range: -3.4518
Max Act: 3.2479. Min Act: -0.1700
Data Index: 3885609 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4518. Min Range: -3.4518
Max Act: 3.2636. Min Act: -0.1700
Data Index: 3795575 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4518. Min Range: -3.4518
Max Act: 3.2322. Min Act: -0.1700
Data Index: 8655592 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4518. Min Range: -3.4518
Max Act: 3.2479. Min Act: -0.1700
Data Index: 6003238 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4518. Min Range: -3.4518
Max Act: 3.2479. Min Act: -0.1700
Data Index: 3974904 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4518. Min Range: -3.4518
Max Act: 3.2636. Min Act: -0.1700
Data Index: 6940341 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4518. Min Range: -3.4518
Max Act: 3.1378. Min Act: -0.1700
Data Index: 5815946 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4518. Min Range: -3.4518
Max Act: 3.2007. Min Act: -0.1700
Data Index: 5353323 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4518. Min Range: -3.4518
Max Act: 3.1535. Min Act: -0.1700
Data Index: 4792553 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4518. Min Range: -3.4518
Max Act: 3.1535. Min Act: -0.1700
Data Index: 6845074 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4518. Min Range: -3.4518
Max Act: 3.1693. Min Act: -0.1700
Data Index: 1963100 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #19