Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1977 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3270. Min Range: -4.3270
Max Act: 4.3270. Min Act: -0.1700
Data Index: 5812669 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3270. Min Range: -4.3270
Max Act: 4.2645. Min Act: -0.1700
Data Index: 5781304 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3270. Min Range: -4.3270
Max Act: 4.0613. Min Act: -0.1700
Data Index: 7261573 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3270. Min Range: -4.3270
Max Act: 4.0144. Min Act: -0.1700
Data Index: 3780881 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3270. Min Range: -4.3270
Max Act: 3.9519. Min Act: -0.1700
Data Index: 1826575 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3270. Min Range: -4.3270
Max Act: 3.9050. Min Act: -0.1700
Data Index: 2281756 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3270. Min Range: -4.3270
Max Act: 3.8268. Min Act: -0.1700
Data Index: 7693662 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3270. Min Range: -4.3270
Max Act: 3.7955. Min Act: -0.1700
Data Index: 4243364 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3270. Min Range: -4.3270
Max Act: 3.7955. Min Act: -0.1700
Data Index: 6927627 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3270. Min Range: -4.3270
Max Act: 3.7643. Min Act: -0.1700
Data Index: 860091 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3270. Min Range: -4.3270
Max Act: 3.7330. Min Act: -0.1700
Data Index: 3949371 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3270. Min Range: -4.3270
Max Act: 3.7330. Min Act: -0.1700
Data Index: 6041386 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3270. Min Range: -4.3270
Max Act: 3.7174. Min Act: -0.1700
Data Index: 7068363 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3270. Min Range: -4.3270
Max Act: 3.7174. Min Act: -0.1700
Data Index: 7872146 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3270. Min Range: -4.3270
Max Act: 3.7017. Min Act: -0.1700
Data Index: 3843205 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3270. Min Range: -4.3270
Max Act: 3.6861. Min Act: -0.1700
Data Index: 4786923 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3270. Min Range: -4.3270
Max Act: 3.6861. Min Act: -0.1700
Data Index: 4627966 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3270. Min Range: -4.3270
Max Act: 3.6548. Min Act: -0.1700
Data Index: 4651230 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3270. Min Range: -4.3270
Max Act: 3.6548. Min Act: -0.1700
Data Index: 813008 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3270. Min Range: -4.3270
Max Act: 3.6548. Min Act: -0.1700
Data Index: 5541771 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #19