Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2547 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0337. Min Range: -7.0337
Max Act: 7.0337. Min Act: -0.1700
Data Index: 2576888 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0337. Min Range: -7.0337
Max Act: 7.0024. Min Act: -0.1700
Data Index: 4213710 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0337. Min Range: -7.0337
Max Act: 6.8149. Min Act: -0.1700
Data Index: 4774677 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0337. Min Range: -7.0337
Max Act: 6.8149. Min Act: -0.1700
Data Index: 6863386 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0337. Min Range: -7.0337
Max Act: 6.7212. Min Act: -0.1700
Data Index: 4933444 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0337. Min Range: -7.0337
Max Act: 6.7212. Min Act: -0.1700
Data Index: 2876857 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0337. Min Range: -7.0337
Max Act: 6.7212. Min Act: -0.1700
Data Index: 7802325 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0337. Min Range: -7.0337
Max Act: 6.6274. Min Act: -0.1700
Data Index: 6809375 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0337. Min Range: -7.0337
Max Act: 6.5962. Min Act: -0.1700
Data Index: 4868904 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0337. Min Range: -7.0337
Max Act: 6.5337. Min Act: -0.1700
Data Index: 4100885 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0337. Min Range: -7.0337
Max Act: 6.5337. Min Act: -0.1700
Data Index: 4645877 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0337. Min Range: -7.0337
Max Act: 6.5337. Min Act: -0.1700
Data Index: 218357 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0337. Min Range: -7.0337
Max Act: 6.4712. Min Act: -0.1700
Data Index: 5529656 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0337. Min Range: -7.0337
Max Act: 6.5649. Min Act: -0.1700
Data Index: 8257476 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0337. Min Range: -7.0337
Max Act: 6.4399. Min Act: -0.1700
Data Index: 6847812 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0337. Min Range: -7.0337
Max Act: 6.4399. Min Act: -0.1700
Data Index: 5662180 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0337. Min Range: -7.0337
Max Act: 6.4399. Min Act: -0.1700
Data Index: 7853119 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0337. Min Range: -7.0337
Max Act: 6.4712. Min Act: -0.1700
Data Index: 1609294 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0337. Min Range: -7.0337
Max Act: 6.3774. Min Act: -0.1700
Data Index: 6837342 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0337. Min Range: -7.0337
Max Act: 6.3774. Min Act: -0.1700
Data Index: 3109100 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #19