Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1936 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1465. Min Range: -3.1465
Max Act: 3.1465. Min Act: -0.1700
Data Index: 83044 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1465. Min Range: -3.1465
Max Act: 3.1150. Min Act: -0.1700
Data Index: 4265244 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1465. Min Range: -3.1465
Max Act: 3.1150. Min Act: -0.1700
Data Index: 5405158 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1465. Min Range: -3.1465
Max Act: 3.1150. Min Act: -0.1700
Data Index: 656803 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1465. Min Range: -3.1465
Max Act: 3.0993. Min Act: -0.1700
Data Index: 7559953 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1465. Min Range: -3.1465
Max Act: 3.0993. Min Act: -0.1700
Data Index: 6178297 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1465. Min Range: -3.1465
Max Act: 3.0835. Min Act: -0.1700
Data Index: 6261005 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1465. Min Range: -3.1465
Max Act: 3.0835. Min Act: -0.1700
Data Index: 8292803 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1465. Min Range: -3.1465
Max Act: 3.0520. Min Act: -0.1700
Data Index: 503289 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1465. Min Range: -3.1465
Max Act: 3.0520. Min Act: -0.1700
Data Index: 2344321 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1465. Min Range: -3.1465
Max Act: 3.0520. Min Act: -0.1700
Data Index: 1676686 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1465. Min Range: -3.1465
Max Act: 3.0520. Min Act: -0.1700
Data Index: 4081545 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1465. Min Range: -3.1465
Max Act: 3.0677. Min Act: -0.1700
Data Index: 7007601 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1465. Min Range: -3.1465
Max Act: 3.0362. Min Act: -0.1700
Data Index: 6123116 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1465. Min Range: -3.1465
Max Act: 3.0520. Min Act: -0.1700
Data Index: 6450187 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1465. Min Range: -3.1465
Max Act: 3.0362. Min Act: -0.1700
Data Index: 1216766 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1465. Min Range: -3.1465
Max Act: 3.0520. Min Act: -0.1700
Data Index: 7330794 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1465. Min Range: -3.1465
Max Act: 2.9888. Min Act: -0.1700
Data Index: 4917308 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1465. Min Range: -3.1465
Max Act: 3.0046. Min Act: -0.1700
Data Index: 3603122 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1465. Min Range: -3.1465
Max Act: 3.0204. Min Act: -0.1700
Data Index: 5276417 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #19