Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3010 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8441. Min Range: -3.8441
Max Act: 3.8441. Min Act: -0.1700
Data Index: 6550531 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8441. Min Range: -3.8441
Max Act: 3.8129. Min Act: -0.1700
Data Index: 4159176 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8441. Min Range: -3.8441
Max Act: 3.8129. Min Act: -0.1700
Data Index: 8780164 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8441. Min Range: -3.8441
Max Act: 3.7660. Min Act: -0.1700
Data Index: 3589689 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8441. Min Range: -3.8441
Max Act: 3.7660. Min Act: -0.1700
Data Index: 425674 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8441. Min Range: -3.8441
Max Act: 3.7503. Min Act: -0.1700
Data Index: 1068583 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8441. Min Range: -3.8441
Max Act: 3.7503. Min Act: -0.1700
Data Index: 5353873 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8441. Min Range: -3.8441
Max Act: 3.7503. Min Act: -0.1700
Data Index: 5473443 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8441. Min Range: -3.8441
Max Act: 3.7347. Min Act: -0.1700
Data Index: 3228718 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8441. Min Range: -3.8441
Max Act: 3.7034. Min Act: -0.1700
Data Index: 1098070 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8441. Min Range: -3.8441
Max Act: 3.7034. Min Act: -0.1700
Data Index: 7511959 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8441. Min Range: -3.8441
Max Act: 3.7034. Min Act: -0.1700
Data Index: 5536068 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8441. Min Range: -3.8441
Max Act: 3.6878. Min Act: -0.1700
Data Index: 6778269 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8441. Min Range: -3.8441
Max Act: 3.7034. Min Act: -0.1700
Data Index: 7452503 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8441. Min Range: -3.8441
Max Act: 3.6878. Min Act: -0.1700
Data Index: 601969 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8441. Min Range: -3.8441
Max Act: 3.6878. Min Act: -0.1700
Data Index: 949322 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8441. Min Range: -3.8441
Max Act: 3.6878. Min Act: -0.1700
Data Index: 474203 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8441. Min Range: -3.8441
Max Act: 3.6721. Min Act: -0.1700
Data Index: 7441086 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8441. Min Range: -3.8441
Max Act: 3.6721. Min Act: -0.1700
Data Index: 6095525 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8441. Min Range: -3.8441
Max Act: 3.6878. Min Act: -0.1700
Data Index: 5826832 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19