Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3656 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.2559. Min Range: -8.2559
Max Act: 8.2559. Min Act: -0.1700
Data Index: 6338505 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2559. Min Range: -8.2559
Max Act: 8.2246. Min Act: -0.1700
Data Index: 7287038 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2559. Min Range: -8.2559
Max Act: 7.0684. Min Act: -0.1700
Data Index: 3597734 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2559. Min Range: -8.2559
Max Act: 7.8184. Min Act: -0.1700
Data Index: 7287040 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2559. Min Range: -8.2559
Max Act: 7.7871. Min Act: -0.1700
Data Index: 6462498 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2559. Min Range: -8.2559
Max Act: 5.0371. Min Act: -0.1700
Data Index: 4553741 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2559. Min Range: -8.2559
Max Act: 7.1934. Min Act: -0.1700
Data Index: 8201045 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2559. Min Range: -8.2559
Max Act: 7.7559. Min Act: -0.1700
Data Index: 8149784 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2559. Min Range: -8.2559
Max Act: 7.8184. Min Act: -0.1700
Data Index: 4184800 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2559. Min Range: -8.2559
Max Act: 7.7246. Min Act: -0.1700
Data Index: 6462500 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2559. Min Range: -8.2559
Max Act: 6.5684. Min Act: -0.1700
Data Index: 1706017 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2559. Min Range: -8.2559
Max Act: 7.6934. Min Act: -0.1700
Data Index: 8576329 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2559. Min Range: -8.2559
Max Act: 6.3184. Min Act: -0.1700
Data Index: 8011539 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2559. Min Range: -8.2559
Max Act: 7.3496. Min Act: -0.1700
Data Index: 2939088 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2559. Min Range: -8.2559
Max Act: 7.1934. Min Act: -0.1700
Data Index: 3204182 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2559. Min Range: -8.2559
Max Act: 4.7559. Min Act: -0.1700
Data Index: 3414316 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2559. Min Range: -8.2559
Max Act: 7.5996. Min Act: -0.1700
Data Index: 4656961 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2559. Min Range: -8.2559
Max Act: 6.6309. Min Act: -0.1700
Data Index: 4897858 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2559. Min Range: -8.2559
Max Act: 7.7246. Min Act: -0.1700
Data Index: 2225554 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2559. Min Range: -8.2559
Max Act: 6.5059. Min Act: -0.1700
Data Index: 5780765 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19