Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4464 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0656. Min Range: -9.0656
Max Act: 9.0656. Min Act: -0.1700
Data Index: 5967939 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0656. Min Range: -9.0656
Max Act: 8.3781. Min Act: -0.1700
Data Index: 3180394 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0656. Min Range: -9.0656
Max Act: 8.1281. Min Act: -0.1700
Data Index: 4252624 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0656. Min Range: -9.0656
Max Act: 8.1281. Min Act: -0.1700
Data Index: 4730226 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0656. Min Range: -9.0656
Max Act: 8.0656. Min Act: -0.1700
Data Index: 7137024 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0656. Min Range: -9.0656
Max Act: 8.0031. Min Act: -0.1700
Data Index: 80925 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0656. Min Range: -9.0656
Max Act: 8.0031. Min Act: -0.1700
Data Index: 3709796 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0656. Min Range: -9.0656
Max Act: 7.9406. Min Act: -0.1700
Data Index: 4606853 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0656. Min Range: -9.0656
Max Act: 7.9406. Min Act: -0.1700
Data Index: 2370702 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0656. Min Range: -9.0656
Max Act: 7.9406. Min Act: -0.1700
Data Index: 4359982 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0656. Min Range: -9.0656
Max Act: 7.8781. Min Act: -0.1700
Data Index: 4934344 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0656. Min Range: -9.0656
Max Act: 7.8781. Min Act: -0.1700
Data Index: 4484691 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0656. Min Range: -9.0656
Max Act: 7.8781. Min Act: -0.1700
Data Index: 6215682 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0656. Min Range: -9.0656
Max Act: 7.8156. Min Act: -0.1700
Data Index: 7966972 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0656. Min Range: -9.0656
Max Act: 7.8156. Min Act: -0.1700
Data Index: 1685209 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0656. Min Range: -9.0656
Max Act: 7.8156. Min Act: -0.1700
Data Index: 4070958 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0656. Min Range: -9.0656
Max Act: 7.8156. Min Act: -0.1700
Data Index: 3628701 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0656. Min Range: -9.0656
Max Act: 7.7531. Min Act: -0.1700
Data Index: 303113 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0656. Min Range: -9.0656
Max Act: 7.6906. Min Act: -0.1700
Data Index: 4695243 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0656. Min Range: -9.0656
Max Act: 7.7531. Min Act: -0.1700
Data Index: 6445717 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19