Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 69 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2688. Min Range: -6.2688
Max Act: 6.2063. Min Act: -0.1700
Data Index: 6357171 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2688. Min Range: -6.2688
Max Act: 6.2688. Min Act: -0.1700
Data Index: 5181691 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2688. Min Range: -6.2688
Max Act: 6.1126. Min Act: -0.1700
Data Index: 5685703 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2688. Min Range: -6.2688
Max Act: 6.0813. Min Act: -0.1700
Data Index: 4429605 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2688. Min Range: -6.2688
Max Act: 6.0813. Min Act: -0.1700
Data Index: 7149508 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2688. Min Range: -6.2688
Max Act: 6.0813. Min Act: -0.1700
Data Index: 305972 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2688. Min Range: -6.2688
Max Act: 6.0188. Min Act: -0.1700
Data Index: 4644391 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2688. Min Range: -6.2688
Max Act: 5.9251. Min Act: -0.1700
Data Index: 930696 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2688. Min Range: -6.2688
Max Act: 5.9563. Min Act: -0.1700
Data Index: 2862630 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2688. Min Range: -6.2688
Max Act: 5.9563. Min Act: -0.1700
Data Index: 496569 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2688. Min Range: -6.2688
Max Act: 5.9251. Min Act: -0.1700
Data Index: 1082955 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2688. Min Range: -6.2688
Max Act: 5.8938. Min Act: -0.1700
Data Index: 4607977 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2688. Min Range: -6.2688
Max Act: 5.8938. Min Act: -0.1700
Data Index: 1561480 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2688. Min Range: -6.2688
Max Act: 5.8938. Min Act: -0.1700
Data Index: 7833920 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2688. Min Range: -6.2688
Max Act: 5.8313. Min Act: -0.1700
Data Index: 2295550 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2688. Min Range: -6.2688
Max Act: 5.8938. Min Act: -0.1700
Data Index: 181034 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2688. Min Range: -6.2688
Max Act: 5.8313. Min Act: -0.1700
Data Index: 7232255 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2688. Min Range: -6.2688
Max Act: 5.8001. Min Act: -0.1700
Data Index: 280368 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2688. Min Range: -6.2688
Max Act: 5.8001. Min Act: -0.1700
Data Index: 2830780 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2688. Min Range: -6.2688
Max Act: 5.8313. Min Act: -0.1700
Data Index: 7580754 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19