Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2014 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4332. Min Range: -4.4332
Max Act: 4.4332. Min Act: -0.1700
Data Index: 5874128 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4332. Min Range: -4.4332
Max Act: 4.4332. Min Act: -0.1700
Data Index: 6783252 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4332. Min Range: -4.4332
Max Act: 4.4019. Min Act: -0.1700
Data Index: 63387 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4332. Min Range: -4.4332
Max Act: 4.3707. Min Act: -0.1700
Data Index: 3720110 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4332. Min Range: -4.4332
Max Act: 4.4019. Min Act: -0.1700
Data Index: 7980367 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4332. Min Range: -4.4332
Max Act: 4.3707. Min Act: -0.1700
Data Index: 2699 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4332. Min Range: -4.4332
Max Act: 4.3394. Min Act: -0.1700
Data Index: 5620761 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4332. Min Range: -4.4332
Max Act: 4.3707. Min Act: -0.1700
Data Index: 8020436 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4332. Min Range: -4.4332
Max Act: 4.3082. Min Act: -0.1700
Data Index: 4063775 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4332. Min Range: -4.4332
Max Act: 4.3082. Min Act: -0.1700
Data Index: 867001 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4332. Min Range: -4.4332
Max Act: 4.3082. Min Act: -0.1700
Data Index: 3664199 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4332. Min Range: -4.4332
Max Act: 4.3082. Min Act: -0.1700
Data Index: 5807779 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4332. Min Range: -4.4332
Max Act: 4.3394. Min Act: -0.1700
Data Index: 7402196 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4332. Min Range: -4.4332
Max Act: 4.2769. Min Act: -0.1700
Data Index: 5679795 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4332. Min Range: -4.4332
Max Act: 4.3082. Min Act: -0.1700
Data Index: 791078 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4332. Min Range: -4.4332
Max Act: 4.3082. Min Act: -0.1700
Data Index: 204617 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4332. Min Range: -4.4332
Max Act: 4.3082. Min Act: -0.1700
Data Index: 2813181 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4332. Min Range: -4.4332
Max Act: 4.2457. Min Act: -0.1700
Data Index: 7889863 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4332. Min Range: -4.4332
Max Act: 4.2457. Min Act: -0.1700
Data Index: 120708 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4332. Min Range: -4.4332
Max Act: 4.2769. Min Act: -0.1700
Data Index: 5071806 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19