Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2652 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9588. Min Range: -2.9588
Max Act: 2.9588. Min Act: -0.1700
Data Index: 6558935 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9588. Min Range: -2.9588
Max Act: 2.8954. Min Act: -0.1700
Data Index: 3101733 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9588. Min Range: -2.9588
Max Act: 2.8636. Min Act: -0.1700
Data Index: 1617667 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9588. Min Range: -2.9588
Max Act: 2.8319. Min Act: -0.1700
Data Index: 4361862 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9588. Min Range: -2.9588
Max Act: 2.8160. Min Act: -0.1700
Data Index: 7663211 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9588. Min Range: -2.9588
Max Act: 2.8160. Min Act: -0.1700
Data Index: 1203647 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9588. Min Range: -2.9588
Max Act: 2.8000. Min Act: -0.1700
Data Index: 1661229 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9588. Min Range: -2.9588
Max Act: 2.7841. Min Act: -0.1700
Data Index: 1213718 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9588. Min Range: -2.9588
Max Act: 2.7841. Min Act: -0.1700
Data Index: 5541776 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9588. Min Range: -2.9588
Max Act: 2.7841. Min Act: -0.1700
Data Index: 1337357 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9588. Min Range: -2.9588
Max Act: 2.7841. Min Act: -0.1700
Data Index: 2792064 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9588. Min Range: -2.9588
Max Act: 2.7841. Min Act: -0.1700
Data Index: 3450789 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9588. Min Range: -2.9588
Max Act: 2.7841. Min Act: -0.1700
Data Index: 3030655 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9588. Min Range: -2.9588
Max Act: 2.7841. Min Act: -0.1700
Data Index: 2267719 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9588. Min Range: -2.9588
Max Act: 2.8000. Min Act: -0.1700
Data Index: 619633 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9588. Min Range: -2.9588
Max Act: 2.7841. Min Act: -0.1700
Data Index: 730772 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9588. Min Range: -2.9588
Max Act: 2.7522. Min Act: -0.1700
Data Index: 3900530 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9588. Min Range: -2.9588
Max Act: 2.7362. Min Act: -0.1700
Data Index: 3268608 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9588. Min Range: -2.9588
Max Act: 2.7522. Min Act: -0.1700
Data Index: 6122841 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9588. Min Range: -2.9588
Max Act: 2.7522. Min Act: -0.1700
Data Index: 7674043 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19