Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3311 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8647. Min Range: -3.8647
Max Act: 3.8335. Min Act: -0.1700
Data Index: 1153741 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8647. Min Range: -3.8647
Max Act: 3.8647. Min Act: -0.1700
Data Index: 1908049 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8647. Min Range: -3.8647
Max Act: 3.8647. Min Act: -0.1700
Data Index: 136930 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8647. Min Range: -3.8647
Max Act: 3.8022. Min Act: -0.1700
Data Index: 6877 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8647. Min Range: -3.8647
Max Act: 3.8022. Min Act: -0.1700
Data Index: 3203753 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8647. Min Range: -3.8647
Max Act: 3.7709. Min Act: -0.1700
Data Index: 826379 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8647. Min Range: -3.8647
Max Act: 3.7396. Min Act: -0.1700
Data Index: 4448641 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8647. Min Range: -3.8647
Max Act: 3.7709. Min Act: -0.1700
Data Index: 3111366 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8647. Min Range: -3.8647
Max Act: 3.7396. Min Act: -0.1700
Data Index: 2544022 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8647. Min Range: -3.8647
Max Act: 3.7709. Min Act: -0.1700
Data Index: 5763113 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8647. Min Range: -3.8647
Max Act: 3.7396. Min Act: -0.1700
Data Index: 5340839 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8647. Min Range: -3.8647
Max Act: 3.7084. Min Act: -0.1700
Data Index: 7470903 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8647. Min Range: -3.8647
Max Act: 3.7084. Min Act: -0.1700
Data Index: 13147 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8647. Min Range: -3.8647
Max Act: 3.7084. Min Act: -0.1700
Data Index: 2926644 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8647. Min Range: -3.8647
Max Act: 3.7084. Min Act: -0.1700
Data Index: 515985 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8647. Min Range: -3.8647
Max Act: 3.6771. Min Act: -0.1700
Data Index: 893418 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8647. Min Range: -3.8647
Max Act: 3.6771. Min Act: -0.1700
Data Index: 1131900 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8647. Min Range: -3.8647
Max Act: 3.6771. Min Act: -0.1700
Data Index: 628188 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8647. Min Range: -3.8647
Max Act: 3.7084. Min Act: -0.1700
Data Index: 4587980 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8647. Min Range: -3.8647
Max Act: 3.6458. Min Act: -0.1700
Data Index: 5198814 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #19