Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2753 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.5504. Min Act: -0.1700
Data Index: 6427633 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.3941. Min Act: -0.1700
Data Index: 4957696 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.3941. Min Act: -0.1700
Data Index: 2297339 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.3941. Min Act: -0.1700
Data Index: 5363746 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.3941. Min Act: -0.1700
Data Index: 1568292 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.3629. Min Act: -0.1700
Data Index: 5824684 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.3004. Min Act: -0.1700
Data Index: 6506338 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.2691. Min Act: -0.1700
Data Index: 3344015 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.2379. Min Act: -0.1700
Data Index: 6049069 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.2691. Min Act: -0.1700
Data Index: 1453098 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.2066. Min Act: -0.1700
Data Index: 4855270 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.1754. Min Act: -0.1700
Data Index: 3051262 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.2066. Min Act: -0.1700
Data Index: 6438846 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.1754. Min Act: -0.1700
Data Index: 8154955 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.1441. Min Act: -0.1700
Data Index: 5340441 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.1754. Min Act: -0.1700
Data Index: 2509107 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.1754. Min Act: -0.1700
Data Index: 2479295 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.1441. Min Act: -0.1700
Data Index: 1514753 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.1754. Min Act: -0.1700
Data Index: 3322290 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.1441. Min Act: -0.1700
Data Index: 2111895 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19