Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2505 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3076. Min Range: -3.3076
Max Act: 3.3076. Min Act: -0.1700
Data Index: 7686541 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3076. Min Range: -3.3076
Max Act: 3.2290. Min Act: -0.1700
Data Index: 5017291 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3076. Min Range: -3.3076
Max Act: 3.1976. Min Act: -0.1700
Data Index: 7087741 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3076. Min Range: -3.3076
Max Act: 3.1976. Min Act: -0.1700
Data Index: 7686542 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3076. Min Range: -3.3076
Max Act: 3.1661. Min Act: -0.1700
Data Index: 5975016 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3076. Min Range: -3.3076
Max Act: 3.1819. Min Act: -0.1700
Data Index: 4315738 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3076. Min Range: -3.3076
Max Act: 3.1661. Min Act: -0.1700
Data Index: 2107430 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3076. Min Range: -3.3076
Max Act: 3.1504. Min Act: -0.1700
Data Index: 4004029 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3076. Min Range: -3.3076
Max Act: 3.1661. Min Act: -0.1700
Data Index: 5444021 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3076. Min Range: -3.3076
Max Act: 3.1347. Min Act: -0.1700
Data Index: 4875417 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3076. Min Range: -3.3076
Max Act: 3.0874. Min Act: -0.1700
Data Index: 8538663 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3076. Min Range: -3.3076
Max Act: 3.0716. Min Act: -0.1700
Data Index: 7864088 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3076. Min Range: -3.3076
Max Act: 3.0874. Min Act: -0.1700
Data Index: 6853472 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3076. Min Range: -3.3076
Max Act: 3.1031. Min Act: -0.1700
Data Index: 6237116 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3076. Min Range: -3.3076
Max Act: 3.0874. Min Act: -0.1700
Data Index: 6853471 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3076. Min Range: -3.3076
Max Act: 3.0874. Min Act: -0.1700
Data Index: 5221269 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3076. Min Range: -3.3076
Max Act: 3.0558. Min Act: -0.1700
Data Index: 5161037 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3076. Min Range: -3.3076
Max Act: 3.0716. Min Act: -0.1700
Data Index: 4888254 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3076. Min Range: -3.3076
Max Act: 3.0716. Min Act: -0.1700
Data Index: 4479140 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3076. Min Range: -3.3076
Max Act: 3.0401. Min Act: -0.1700
Data Index: 6251579 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #19