Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1602 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9303. Min Range: -4.9303
Max Act: 4.9303. Min Act: -0.1700
Data Index: 5326634 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9303. Min Range: -4.9303
Max Act: 4.8365. Min Act: -0.1700
Data Index: 6446950 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9303. Min Range: -4.9303
Max Act: 4.8053. Min Act: -0.1700
Data Index: 8729610 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9303. Min Range: -4.9303
Max Act: 4.8053. Min Act: -0.1700
Data Index: 6874037 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9303. Min Range: -4.9303
Max Act: 4.7428. Min Act: -0.1700
Data Index: 1439952 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9303. Min Range: -4.9303
Max Act: 4.7428. Min Act: -0.1700
Data Index: 5875953 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9303. Min Range: -4.9303
Max Act: 4.7428. Min Act: -0.1700
Data Index: 1168380 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9303. Min Range: -4.9303
Max Act: 4.7115. Min Act: -0.1700
Data Index: 184963 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9303. Min Range: -4.9303
Max Act: 4.7115. Min Act: -0.1700
Data Index: 6499279 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9303. Min Range: -4.9303
Max Act: 4.7115. Min Act: -0.1700
Data Index: 5143610 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9303. Min Range: -4.9303
Max Act: 4.6803. Min Act: -0.1700
Data Index: 6032539 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9303. Min Range: -4.9303
Max Act: 4.6803. Min Act: -0.1700
Data Index: 3682945 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9303. Min Range: -4.9303
Max Act: 4.6490. Min Act: -0.1700
Data Index: 1965534 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9303. Min Range: -4.9303
Max Act: 4.6490. Min Act: -0.1700
Data Index: 6147391 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9303. Min Range: -4.9303
Max Act: 4.6490. Min Act: -0.1700
Data Index: 7633824 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9303. Min Range: -4.9303
Max Act: 4.6490. Min Act: -0.1700
Data Index: 7420462 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9303. Min Range: -4.9303
Max Act: 4.6490. Min Act: -0.1700
Data Index: 7202093 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9303. Min Range: -4.9303
Max Act: 4.6490. Min Act: -0.1700
Data Index: 7106246 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9303. Min Range: -4.9303
Max Act: 4.6490. Min Act: -0.1700
Data Index: 1513356 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9303. Min Range: -4.9303
Max Act: 4.6178. Min Act: -0.1700
Data Index: 4867525 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19