Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 499 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.1491. Min Range: -11.1491
Max Act: 11.1491. Min Act: -0.1700
Data Index: 4513891 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.1491. Min Range: -11.1491
Max Act: 11.0866. Min Act: -0.1700
Data Index: 1246522 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.1491. Min Range: -11.1491
Max Act: 11.0866. Min Act: -0.1700
Data Index: 7816902 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.1491. Min Range: -11.1491
Max Act: 11.0866. Min Act: -0.1700
Data Index: 4373665 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.1491. Min Range: -11.1491
Max Act: 10.8991. Min Act: -0.1700
Data Index: 3278093 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.1491. Min Range: -11.1491
Max Act: 10.8991. Min Act: -0.1700
Data Index: 7893145 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.1491. Min Range: -11.1491
Max Act: 10.8366. Min Act: -0.1700
Data Index: 8579967 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.1491. Min Range: -11.1491
Max Act: 10.8991. Min Act: -0.1700
Data Index: 1956619 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.1491. Min Range: -11.1491
Max Act: 10.8991. Min Act: -0.1700
Data Index: 318343 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.1491. Min Range: -11.1491
Max Act: 10.8366. Min Act: -0.1700
Data Index: 614379 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.1491. Min Range: -11.1491
Max Act: 10.8366. Min Act: -0.1700
Data Index: 3389678 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.1491. Min Range: -11.1491
Max Act: 10.8366. Min Act: -0.1700
Data Index: 4005018 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.1491. Min Range: -11.1491
Max Act: 10.7741. Min Act: -0.1700
Data Index: 197632 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.1491. Min Range: -11.1491
Max Act: 10.7741. Min Act: -0.1700
Data Index: 4263327 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.1491. Min Range: -11.1491
Max Act: 10.7116. Min Act: -0.1700
Data Index: 6689365 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.1491. Min Range: -11.1491
Max Act: 10.7116. Min Act: -0.1700
Data Index: 86486 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.1491. Min Range: -11.1491
Max Act: 10.7116. Min Act: -0.1700
Data Index: 8301272 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.1491. Min Range: -11.1491
Max Act: 10.6491. Min Act: -0.1700
Data Index: 2221973 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.1491. Min Range: -11.1491
Max Act: 10.7116. Min Act: -0.1700
Data Index: 2024732 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.1491. Min Range: -11.1491
Max Act: 10.7116. Min Act: -0.1700
Data Index: 8782774 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #19