Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1077 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5125. Min Range: -6.5125
Max Act: 6.5125. Min Act: -0.1700
Data Index: 4723480 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5125. Min Range: -6.5125
Max Act: 6.2938. Min Act: -0.1700
Data Index: 709612 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5125. Min Range: -6.5125
Max Act: 6.2625. Min Act: -0.1700
Data Index: 709613 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5125. Min Range: -6.5125
Max Act: 6.2000. Min Act: -0.1700
Data Index: 4108228 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5125. Min Range: -6.5125
Max Act: 6.0750. Min Act: -0.1700
Data Index: 1819188 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5125. Min Range: -6.5125
Max Act: 5.9813. Min Act: -0.1700
Data Index: 4193819 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5125. Min Range: -6.5125
Max Act: 5.8563. Min Act: -0.1700
Data Index: 678770 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5125. Min Range: -6.5125
Max Act: 5.7313. Min Act: -0.1700
Data Index: 3537311 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5125. Min Range: -6.5125
Max Act: 5.7313. Min Act: -0.1700
Data Index: 565176 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5125. Min Range: -6.5125
Max Act: 5.7313. Min Act: -0.1700
Data Index: 259044 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5125. Min Range: -6.5125
Max Act: 5.6688. Min Act: -0.1700
Data Index: 8567616 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5125. Min Range: -6.5125
Max Act: 5.6688. Min Act: -0.1700
Data Index: 2456415 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5125. Min Range: -6.5125
Max Act: 5.6688. Min Act: -0.1700
Data Index: 5352562 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5125. Min Range: -6.5125
Max Act: 5.6688. Min Act: -0.1700
Data Index: 5967393 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5125. Min Range: -6.5125
Max Act: 5.6375. Min Act: -0.1700
Data Index: 5000201 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5125. Min Range: -6.5125
Max Act: 5.6375. Min Act: -0.1700
Data Index: 1831895 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5125. Min Range: -6.5125
Max Act: 5.6063. Min Act: -0.1700
Data Index: 3276581 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5125. Min Range: -6.5125
Max Act: 5.5750. Min Act: -0.1700
Data Index: 5517343 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5125. Min Range: -6.5125
Max Act: 5.6063. Min Act: -0.1700
Data Index: 7039715 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5125. Min Range: -6.5125
Max Act: 5.5750. Min Act: -0.1700
Data Index: 905025 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #19