Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3150 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3795. Min Range: -9.3795
Max Act: 9.3795. Min Act: -0.1700
Data Index: 967939 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3795. Min Range: -9.3795
Max Act: 9.2545. Min Act: -0.1700
Data Index: 2382430 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3795. Min Range: -9.3795
Max Act: 8.7545. Min Act: -0.1700
Data Index: 1641797 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3795. Min Range: -9.3795
Max Act: 8.6920. Min Act: -0.1700
Data Index: 6886409 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3795. Min Range: -9.3795
Max Act: 8.5045. Min Act: -0.1700
Data Index: 3366940 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3795. Min Range: -9.3795
Max Act: 8.4420. Min Act: -0.1700
Data Index: 1986142 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3795. Min Range: -9.3795
Max Act: 8.3170. Min Act: -0.1700
Data Index: 2258178 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3795. Min Range: -9.3795
Max Act: 8.3795. Min Act: -0.1700
Data Index: 8276982 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3795. Min Range: -9.3795
Max Act: 8.3795. Min Act: -0.1700
Data Index: 8207065 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3795. Min Range: -9.3795
Max Act: 8.2232. Min Act: -0.1700
Data Index: 6353234 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3795. Min Range: -9.3795
Max Act: 8.2232. Min Act: -0.1700
Data Index: 3270565 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3795. Min Range: -9.3795
Max Act: 8.1920. Min Act: -0.1700
Data Index: 535937 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3795. Min Range: -9.3795
Max Act: 8.2232. Min Act: -0.1700
Data Index: 2080992 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3795. Min Range: -9.3795
Max Act: 8.2232. Min Act: -0.1700
Data Index: 5239977 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3795. Min Range: -9.3795
Max Act: 8.1607. Min Act: -0.1700
Data Index: 6377746 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3795. Min Range: -9.3795
Max Act: 8.0670. Min Act: -0.1700
Data Index: 2274438 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3795. Min Range: -9.3795
Max Act: 8.0357. Min Act: -0.1700
Data Index: 3542387 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3795. Min Range: -9.3795
Max Act: 8.0045. Min Act: -0.1700
Data Index: 7818200 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3795. Min Range: -9.3795
Max Act: 8.0045. Min Act: -0.1700
Data Index: 3656884 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3795. Min Range: -9.3795
Max Act: 8.0045. Min Act: -0.1700
Data Index: 2464362 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19