Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4724 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3771. Min Range: -9.3771
Max Act: 9.3771. Min Act: -0.1700
Data Index: 617514 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3771. Min Range: -9.3771
Max Act: 9.3146. Min Act: -0.1700
Data Index: 2611532 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3771. Min Range: -9.3771
Max Act: 9.0021. Min Act: -0.1700
Data Index: 601330 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3771. Min Range: -9.3771
Max Act: 9.0021. Min Act: -0.1700
Data Index: 202190 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3771. Min Range: -9.3771
Max Act: 8.7521. Min Act: -0.1700
Data Index: 38323 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3771. Min Range: -9.3771
Max Act: 8.6896. Min Act: -0.1700
Data Index: 2400760 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3771. Min Range: -9.3771
Max Act: 8.6896. Min Act: -0.1700
Data Index: 5261558 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3771. Min Range: -9.3771
Max Act: 8.6271. Min Act: -0.1700
Data Index: 3194070 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3771. Min Range: -9.3771
Max Act: 8.6271. Min Act: -0.1700
Data Index: 2759533 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3771. Min Range: -9.3771
Max Act: 8.6271. Min Act: -0.1700
Data Index: 2749659 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3771. Min Range: -9.3771
Max Act: 8.5646. Min Act: -0.1700
Data Index: 6821737 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3771. Min Range: -9.3771
Max Act: 8.3771. Min Act: -0.1700
Data Index: 4614655 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3771. Min Range: -9.3771
Max Act: 8.3771. Min Act: -0.1700
Data Index: 8511046 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3771. Min Range: -9.3771
Max Act: 8.2521. Min Act: -0.1700
Data Index: 8488459 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3771. Min Range: -9.3771
Max Act: 8.2521. Min Act: -0.1700
Data Index: 1083299 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3771. Min Range: -9.3771
Max Act: 8.2521. Min Act: -0.1700
Data Index: 4036499 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3771. Min Range: -9.3771
Max Act: 8.1896. Min Act: -0.1700
Data Index: 258140 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3771. Min Range: -9.3771
Max Act: 8.1896. Min Act: -0.1700
Data Index: 2278643 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3771. Min Range: -9.3771
Max Act: 8.1271. Min Act: -0.1700
Data Index: 1352082 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3771. Min Range: -9.3771
Max Act: 8.0646. Min Act: -0.1700
Data Index: 1848602 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19