Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3189 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7832. Min Range: -6.7832
Max Act: 6.7832. Min Act: -0.1700
Data Index: 116574 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7832. Min Range: -6.7832
Max Act: 6.6582. Min Act: -0.1700
Data Index: 4875468 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7832. Min Range: -6.7832
Max Act: 6.6270. Min Act: -0.1700
Data Index: 4895582 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7832. Min Range: -6.7832
Max Act: 6.5957. Min Act: -0.1700
Data Index: 5292064 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7832. Min Range: -6.7832
Max Act: 6.5645. Min Act: -0.1700
Data Index: 3415045 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7832. Min Range: -6.7832
Max Act: 6.5957. Min Act: -0.1700
Data Index: 6395841 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7832. Min Range: -6.7832
Max Act: 6.5332. Min Act: -0.1700
Data Index: 5509288 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7832. Min Range: -6.7832
Max Act: 6.5020. Min Act: -0.1700
Data Index: 4154856 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7832. Min Range: -6.7832
Max Act: 6.5020. Min Act: -0.1700
Data Index: 1651417 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7832. Min Range: -6.7832
Max Act: 6.4707. Min Act: -0.1700
Data Index: 3850712 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7832. Min Range: -6.7832
Max Act: 6.4707. Min Act: -0.1700
Data Index: 331279 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7832. Min Range: -6.7832
Max Act: 6.4395. Min Act: -0.1700
Data Index: 7607893 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7832. Min Range: -6.7832
Max Act: 6.4395. Min Act: -0.1700
Data Index: 3891442 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7832. Min Range: -6.7832
Max Act: 6.4082. Min Act: -0.1700
Data Index: 5936160 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7832. Min Range: -6.7832
Max Act: 6.3457. Min Act: -0.1700
Data Index: 3085154 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7832. Min Range: -6.7832
Max Act: 6.3457. Min Act: -0.1700
Data Index: 3420503 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7832. Min Range: -6.7832
Max Act: 6.3457. Min Act: -0.1700
Data Index: 7151556 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7832. Min Range: -6.7832
Max Act: 6.3145. Min Act: -0.1700
Data Index: 5911311 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7832. Min Range: -6.7832
Max Act: 6.3145. Min Act: -0.1700
Data Index: 7279516 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7832. Min Range: -6.7832
Max Act: 6.2832. Min Act: -0.1700
Data Index: 4582794 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #19