Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 803 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2422. Min Range: -3.2422
Max Act: 3.2422. Min Act: -0.1700
Data Index: 1891444 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2422. Min Range: -3.2422
Max Act: 3.1793. Min Act: -0.1700
Data Index: 2915943 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2422. Min Range: -3.2422
Max Act: 3.1479. Min Act: -0.1700
Data Index: 6672338 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2422. Min Range: -3.2422
Max Act: 3.1479. Min Act: -0.1700
Data Index: 1071172 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2422. Min Range: -3.2422
Max Act: 3.1006. Min Act: -0.1700
Data Index: 2673312 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2422. Min Range: -3.2422
Max Act: 3.1006. Min Act: -0.1700
Data Index: 181619 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2422. Min Range: -3.2422
Max Act: 3.1006. Min Act: -0.1700
Data Index: 8509568 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2422. Min Range: -3.2422
Max Act: 3.0691. Min Act: -0.1700
Data Index: 1367882 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2422. Min Range: -3.2422
Max Act: 3.0375. Min Act: -0.1700
Data Index: 2207022 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2422. Min Range: -3.2422
Max Act: 3.0691. Min Act: -0.1700
Data Index: 5850690 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2422. Min Range: -3.2422
Max Act: 3.0533. Min Act: -0.1700
Data Index: 4099468 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2422. Min Range: -3.2422
Max Act: 3.0533. Min Act: -0.1700
Data Index: 8020229 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2422. Min Range: -3.2422
Max Act: 3.0533. Min Act: -0.1700
Data Index: 8405587 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2422. Min Range: -3.2422
Max Act: 3.0059. Min Act: -0.1700
Data Index: 1138969 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2422. Min Range: -3.2422
Max Act: 3.0059. Min Act: -0.1700
Data Index: 2524007 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2422. Min Range: -3.2422
Max Act: 3.0059. Min Act: -0.1700
Data Index: 1603906 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2422. Min Range: -3.2422
Max Act: 3.0059. Min Act: -0.1700
Data Index: 7462521 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2422. Min Range: -3.2422
Max Act: 3.0059. Min Act: -0.1700
Data Index: 4536271 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2422. Min Range: -3.2422
Max Act: 3.0059. Min Act: -0.1700
Data Index: 7750625 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2422. Min Range: -3.2422
Max Act: 3.0059. Min Act: -0.1700
Data Index: 2830564 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19