Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4074 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.4784. Min Range: -7.4784
Max Act: 7.4784. Min Act: -0.1700
Data Index: 1878148 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4784. Min Range: -7.4784
Max Act: 7.2284. Min Act: -0.1700
Data Index: 1093556 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4784. Min Range: -7.4784
Max Act: 7.2597. Min Act: -0.1700
Data Index: 6687107 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4784. Min Range: -7.4784
Max Act: 7.2284. Min Act: -0.1700
Data Index: 6219543 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4784. Min Range: -7.4784
Max Act: 7.1347. Min Act: -0.1700
Data Index: 1882542 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4784. Min Range: -7.4784
Max Act: 7.1347. Min Act: -0.1700
Data Index: 1820134 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4784. Min Range: -7.4784
Max Act: 7.1034. Min Act: -0.1700
Data Index: 1403692 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4784. Min Range: -7.4784
Max Act: 7.0722. Min Act: -0.1700
Data Index: 801531 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4784. Min Range: -7.4784
Max Act: 7.0409. Min Act: -0.1700
Data Index: 7326821 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4784. Min Range: -7.4784
Max Act: 7.0097. Min Act: -0.1700
Data Index: 662870 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4784. Min Range: -7.4784
Max Act: 7.0097. Min Act: -0.1700
Data Index: 2091936 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4784. Min Range: -7.4784
Max Act: 6.9784. Min Act: -0.1700
Data Index: 7551801 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4784. Min Range: -7.4784
Max Act: 6.9784. Min Act: -0.1700
Data Index: 2575816 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4784. Min Range: -7.4784
Max Act: 6.9159. Min Act: -0.1700
Data Index: 6832786 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4784. Min Range: -7.4784
Max Act: 6.7597. Min Act: -0.1700
Data Index: 3296694 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4784. Min Range: -7.4784
Max Act: 6.8222. Min Act: -0.1700
Data Index: 5845295 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4784. Min Range: -7.4784
Max Act: 6.7909. Min Act: -0.1700
Data Index: 2163171 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4784. Min Range: -7.4784
Max Act: 6.7597. Min Act: -0.1700
Data Index: 801534 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4784. Min Range: -7.4784
Max Act: 6.8222. Min Act: -0.1700
Data Index: 6991588 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4784. Min Range: -7.4784
Max Act: 6.7909. Min Act: -0.1700
Data Index: 5780639 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #19