Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1891 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4814. Min Range: -4.4814
Max Act: 4.4814. Min Act: -0.1700
Data Index: 7521653 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4814. Min Range: -4.4814
Max Act: 4.2939. Min Act: -0.1700
Data Index: 5844349 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4814. Min Range: -4.4814
Max Act: 4.2626. Min Act: -0.1700
Data Index: 104596 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4814. Min Range: -4.4814
Max Act: 4.2314. Min Act: -0.1700
Data Index: 5039910 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4814. Min Range: -4.4814
Max Act: 4.2626. Min Act: -0.1700
Data Index: 2873278 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4814. Min Range: -4.4814
Max Act: 4.2314. Min Act: -0.1700
Data Index: 2800786 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4814. Min Range: -4.4814
Max Act: 4.1688. Min Act: -0.1700
Data Index: 3574658 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4814. Min Range: -4.4814
Max Act: 4.1376. Min Act: -0.1700
Data Index: 6059352 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4814. Min Range: -4.4814
Max Act: 4.1376. Min Act: -0.1700
Data Index: 1921964 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4814. Min Range: -4.4814
Max Act: 4.1376. Min Act: -0.1700
Data Index: 8597905 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4814. Min Range: -4.4814
Max Act: 4.1063. Min Act: -0.1700
Data Index: 3058530 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4814. Min Range: -4.4814
Max Act: 4.1376. Min Act: -0.1700
Data Index: 3053262 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4814. Min Range: -4.4814
Max Act: 4.1376. Min Act: -0.1700
Data Index: 5366520 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4814. Min Range: -4.4814
Max Act: 4.1376. Min Act: -0.1700
Data Index: 6380920 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4814. Min Range: -4.4814
Max Act: 4.1376. Min Act: -0.1700
Data Index: 2055376 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4814. Min Range: -4.4814
Max Act: 4.1376. Min Act: -0.1700
Data Index: 3346079 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4814. Min Range: -4.4814
Max Act: 4.1063. Min Act: -0.1700
Data Index: 5643528 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4814. Min Range: -4.4814
Max Act: 4.1063. Min Act: -0.1700
Data Index: 200189 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4814. Min Range: -4.4814
Max Act: 4.0751. Min Act: -0.1700
Data Index: 4040967 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4814. Min Range: -4.4814
Max Act: 4.1376. Min Act: -0.1700
Data Index: 2885543 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19