Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2720 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5319. Min Range: -5.5319
Max Act: 5.5319. Min Act: -0.1700
Data Index: 7338568 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5319. Min Range: -5.5319
Max Act: 5.2194. Min Act: -0.1700
Data Index: 1174126 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5319. Min Range: -5.5319
Max Act: 5.2194. Min Act: -0.1700
Data Index: 4779575 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5319. Min Range: -5.5319
Max Act: 5.0631. Min Act: -0.1700
Data Index: 4744683 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5319. Min Range: -5.5319
Max Act: 5.0006. Min Act: -0.1700
Data Index: 5209973 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5319. Min Range: -5.5319
Max Act: 4.9694. Min Act: -0.1700
Data Index: 5123809 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5319. Min Range: -5.5319
Max Act: 4.9694. Min Act: -0.1700
Data Index: 1224301 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5319. Min Range: -5.5319
Max Act: 4.9381. Min Act: -0.1700
Data Index: 5361955 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5319. Min Range: -5.5319
Max Act: 4.9381. Min Act: -0.1700
Data Index: 5727826 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5319. Min Range: -5.5319
Max Act: 4.9069. Min Act: -0.1700
Data Index: 1030819 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5319. Min Range: -5.5319
Max Act: 4.9069. Min Act: -0.1700
Data Index: 8072095 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5319. Min Range: -5.5319
Max Act: 4.9069. Min Act: -0.1700
Data Index: 5609533 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5319. Min Range: -5.5319
Max Act: 4.8756. Min Act: -0.1700
Data Index: 7149020 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5319. Min Range: -5.5319
Max Act: 4.9069. Min Act: -0.1700
Data Index: 7902698 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5319. Min Range: -5.5319
Max Act: 4.8756. Min Act: -0.1700
Data Index: 488310 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5319. Min Range: -5.5319
Max Act: 4.8444. Min Act: -0.1700
Data Index: 8668791 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5319. Min Range: -5.5319
Max Act: 4.8444. Min Act: -0.1700
Data Index: 6874661 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5319. Min Range: -5.5319
Max Act: 4.8444. Min Act: -0.1700
Data Index: 5648383 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5319. Min Range: -5.5319
Max Act: 4.8444. Min Act: -0.1700
Data Index: 5648382 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5319. Min Range: -5.5319
Max Act: 4.8131. Min Act: -0.1700
Data Index: 7804065 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19