Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3235 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0733. Min Range: -6.0733
Max Act: 6.0733. Min Act: -0.1700
Data Index: 5294640 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0733. Min Range: -6.0733
Max Act: 5.9796. Min Act: -0.1700
Data Index: 5596718 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0733. Min Range: -6.0733
Max Act: 5.8858. Min Act: -0.1700
Data Index: 8275291 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0733. Min Range: -6.0733
Max Act: 5.8858. Min Act: -0.1700
Data Index: 6933730 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0733. Min Range: -6.0733
Max Act: 5.7608. Min Act: -0.1700
Data Index: 7380723 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0733. Min Range: -6.0733
Max Act: 5.7296. Min Act: -0.1700
Data Index: 7754836 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0733. Min Range: -6.0733
Max Act: 5.6671. Min Act: -0.1700
Data Index: 7655687 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0733. Min Range: -6.0733
Max Act: 5.6671. Min Act: -0.1700
Data Index: 1536966 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0733. Min Range: -6.0733
Max Act: 5.6983. Min Act: -0.1700
Data Index: 4674270 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0733. Min Range: -6.0733
Max Act: 5.6671. Min Act: -0.1700
Data Index: 4150898 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0733. Min Range: -6.0733
Max Act: 5.5733. Min Act: -0.1700
Data Index: 924796 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0733. Min Range: -6.0733
Max Act: 5.6046. Min Act: -0.1700
Data Index: 5378021 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0733. Min Range: -6.0733
Max Act: 5.6046. Min Act: -0.1700
Data Index: 3475139 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0733. Min Range: -6.0733
Max Act: 5.5733. Min Act: -0.1700
Data Index: 2227261 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0733. Min Range: -6.0733
Max Act: 5.6046. Min Act: -0.1700
Data Index: 315330 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0733. Min Range: -6.0733
Max Act: 5.5733. Min Act: -0.1700
Data Index: 5887459 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0733. Min Range: -6.0733
Max Act: 5.5733. Min Act: -0.1700
Data Index: 1879594 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0733. Min Range: -6.0733
Max Act: 5.5733. Min Act: -0.1700
Data Index: 8271165 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0733. Min Range: -6.0733
Max Act: 5.5421. Min Act: -0.1700
Data Index: 6006852 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0733. Min Range: -6.0733
Max Act: 5.5421. Min Act: -0.1700
Data Index: 412626 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #19