Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4809 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.1552. Min Range: -15.1552
Max Act: 15.1552. Min Act: -0.1700
Data Index: 4735524 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.1552. Min Range: -15.1552
Max Act: 14.7802. Min Act: -0.1700
Data Index: 2350169 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.1552. Min Range: -15.1552
Max Act: 14.2802. Min Act: -0.1700
Data Index: 5578939 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.1552. Min Range: -15.1552
Max Act: 14.2177. Min Act: -0.1700
Data Index: 2483292 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.1552. Min Range: -15.1552
Max Act: 13.9677. Min Act: -0.1700
Data Index: 62732 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.1552. Min Range: -15.1552
Max Act: 13.9052. Min Act: -0.1700
Data Index: 5763342 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.1552. Min Range: -15.1552
Max Act: 13.8427. Min Act: -0.1700
Data Index: 906732 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.1552. Min Range: -15.1552
Max Act: 13.7802. Min Act: -0.1700
Data Index: 2483291 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.1552. Min Range: -15.1552
Max Act: 13.7802. Min Act: -0.1700
Data Index: 611854 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.1552. Min Range: -15.1552
Max Act: 13.7802. Min Act: -0.1700
Data Index: 2905273 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.1552. Min Range: -15.1552
Max Act: 13.7802. Min Act: -0.1700
Data Index: 5763345 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.1552. Min Range: -15.1552
Max Act: 13.7802. Min Act: -0.1700
Data Index: 5763337 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.1552. Min Range: -15.1552
Max Act: 13.8427. Min Act: -0.1700
Data Index: 2777605 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.1552. Min Range: -15.1552
Max Act: 13.7177. Min Act: -0.1700
Data Index: 4103834 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.1552. Min Range: -15.1552
Max Act: 13.6552. Min Act: -0.1700
Data Index: 3664225 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.1552. Min Range: -15.1552
Max Act: 13.6552. Min Act: -0.1700
Data Index: 1106968 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.1552. Min Range: -15.1552
Max Act: 13.5927. Min Act: -0.1700
Data Index: 5763349 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.1552. Min Range: -15.1552
Max Act: 13.6552. Min Act: -0.1700
Data Index: 453712 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.1552. Min Range: -15.1552
Max Act: 13.5302. Min Act: -0.1700
Data Index: 4886291 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.1552. Min Range: -15.1552
Max Act: 13.4677. Min Act: -0.1700
Data Index: 2782549 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19