Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 963 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9948. Min Range: -3.9948
Max Act: 3.9948. Min Act: -0.1700
Data Index: 2936060 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9948. Min Range: -3.9948
Max Act: 3.9636. Min Act: -0.1700
Data Index: 284367 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9948. Min Range: -3.9948
Max Act: 3.9323. Min Act: -0.1700
Data Index: 1129235 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9948. Min Range: -3.9948
Max Act: 3.7916. Min Act: -0.1700
Data Index: 5447542 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9948. Min Range: -3.9948
Max Act: 3.7916. Min Act: -0.1700
Data Index: 254910 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9948. Min Range: -3.9948
Max Act: 3.7603. Min Act: -0.1700
Data Index: 5699237 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9948. Min Range: -3.9948
Max Act: 3.7447. Min Act: -0.1700
Data Index: 3415421 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9948. Min Range: -3.9948
Max Act: 3.7760. Min Act: -0.1700
Data Index: 2205750 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9948. Min Range: -3.9948
Max Act: 3.7603. Min Act: -0.1700
Data Index: 8635004 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9948. Min Range: -3.9948
Max Act: 3.7447. Min Act: -0.1700
Data Index: 4280570 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9948. Min Range: -3.9948
Max Act: 3.7134. Min Act: -0.1700
Data Index: 4791931 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9948. Min Range: -3.9948
Max Act: 3.7134. Min Act: -0.1700
Data Index: 8513104 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9948. Min Range: -3.9948
Max Act: 3.6978. Min Act: -0.1700
Data Index: 3025037 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9948. Min Range: -3.9948
Max Act: 3.7134. Min Act: -0.1700
Data Index: 7561921 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9948. Min Range: -3.9948
Max Act: 3.6978. Min Act: -0.1700
Data Index: 6395657 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9948. Min Range: -3.9948
Max Act: 3.6978. Min Act: -0.1700
Data Index: 8078711 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9948. Min Range: -3.9948
Max Act: 3.6665. Min Act: -0.1700
Data Index: 336943 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9948. Min Range: -3.9948
Max Act: 3.6665. Min Act: -0.1700
Data Index: 4347401 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9948. Min Range: -3.9948
Max Act: 3.6821. Min Act: -0.1700
Data Index: 1703600 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9948. Min Range: -3.9948
Max Act: 3.6665. Min Act: -0.1700
Data Index: 7480668 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #19