Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4089 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5313. Min Range: -3.5313
Max Act: 3.5313. Min Act: -0.1700
Data Index: 5164336 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5313. Min Range: -3.5313
Max Act: 3.5313. Min Act: -0.1700
Data Index: 5347444 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5313. Min Range: -3.5313
Max Act: 3.4530. Min Act: -0.1700
Data Index: 1345757 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5313. Min Range: -3.5313
Max Act: 3.4686. Min Act: -0.1700
Data Index: 2768293 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5313. Min Range: -3.5313
Max Act: 3.4373. Min Act: -0.1700
Data Index: 6173719 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5313. Min Range: -3.5313
Max Act: 3.4843. Min Act: -0.1700
Data Index: 7922030 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5313. Min Range: -3.5313
Max Act: 3.4373. Min Act: -0.1700
Data Index: 52436 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5313. Min Range: -3.5313
Max Act: 3.3746. Min Act: -0.1700
Data Index: 8735095 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5313. Min Range: -3.5313
Max Act: 3.4216. Min Act: -0.1700
Data Index: 3468781 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5313. Min Range: -3.5313
Max Act: 3.4059. Min Act: -0.1700
Data Index: 8106640 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5313. Min Range: -3.5313
Max Act: 3.4059. Min Act: -0.1700
Data Index: 3366319 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5313. Min Range: -3.5313
Max Act: 3.4059. Min Act: -0.1700
Data Index: 7085216 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5313. Min Range: -3.5313
Max Act: 3.3746. Min Act: -0.1700
Data Index: 6536687 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5313. Min Range: -3.5313
Max Act: 3.3903. Min Act: -0.1700
Data Index: 335635 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5313. Min Range: -3.5313
Max Act: 3.3432. Min Act: -0.1700
Data Index: 5382697 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5313. Min Range: -3.5313
Max Act: 3.3432. Min Act: -0.1700
Data Index: 5558076 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5313. Min Range: -3.5313
Max Act: 3.3589. Min Act: -0.1700
Data Index: 3149019 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5313. Min Range: -3.5313
Max Act: 3.3746. Min Act: -0.1700
Data Index: 2296906 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5313. Min Range: -3.5313
Max Act: 3.3275. Min Act: -0.1700
Data Index: 8501001 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5313. Min Range: -3.5313
Max Act: 3.3589. Min Act: -0.1700
Data Index: 5395235 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #19