Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3422 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4255. Min Range: -5.4255
Max Act: 5.4255. Min Act: -0.1700
Data Index: 8138647 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4255. Min Range: -5.4255
Max Act: 5.1442. Min Act: -0.1700
Data Index: 4170124 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4255. Min Range: -5.4255
Max Act: 5.0505. Min Act: -0.1700
Data Index: 3680570 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4255. Min Range: -5.4255
Max Act: 5.0192. Min Act: -0.1700
Data Index: 3057793 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4255. Min Range: -5.4255
Max Act: 4.9880. Min Act: -0.1700
Data Index: 690171 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4255. Min Range: -5.4255
Max Act: 4.9255. Min Act: -0.1700
Data Index: 2806808 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4255. Min Range: -5.4255
Max Act: 4.8942. Min Act: -0.1700
Data Index: 6443023 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4255. Min Range: -5.4255
Max Act: 4.8317. Min Act: -0.1700
Data Index: 7940654 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4255. Min Range: -5.4255
Max Act: 4.8317. Min Act: -0.1700
Data Index: 8420138 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4255. Min Range: -5.4255
Max Act: 4.8630. Min Act: -0.1700
Data Index: 2974872 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4255. Min Range: -5.4255
Max Act: 4.8630. Min Act: -0.1700
Data Index: 23284 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4255. Min Range: -5.4255
Max Act: 4.8630. Min Act: -0.1700
Data Index: 5809720 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4255. Min Range: -5.4255
Max Act: 4.8630. Min Act: -0.1700
Data Index: 3473958 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4255. Min Range: -5.4255
Max Act: 4.9255. Min Act: -0.1700
Data Index: 2000817 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4255. Min Range: -5.4255
Max Act: 4.8630. Min Act: -0.1700
Data Index: 4200543 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4255. Min Range: -5.4255
Max Act: 4.8317. Min Act: -0.1700
Data Index: 2765020 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4255. Min Range: -5.4255
Max Act: 4.8317. Min Act: -0.1700
Data Index: 7302793 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4255. Min Range: -5.4255
Max Act: 4.8005. Min Act: -0.1700
Data Index: 1595599 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4255. Min Range: -5.4255
Max Act: 4.8317. Min Act: -0.1700
Data Index: 4188114 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4255. Min Range: -5.4255
Max Act: 4.8317. Min Act: -0.1700
Data Index: 2488988 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #19