Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1477 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7690. Min Range: -5.7690
Max Act: 5.7690. Min Act: -0.1700
Data Index: 195927 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7690. Min Range: -5.7690
Max Act: 5.6440. Min Act: -0.1700
Data Index: 3911313 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7690. Min Range: -5.7690
Max Act: 5.6440. Min Act: -0.1700
Data Index: 1783075 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7690. Min Range: -5.7690
Max Act: 5.6128. Min Act: -0.1700
Data Index: 6752750 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7690. Min Range: -5.7690
Max Act: 5.5503. Min Act: -0.1700
Data Index: 6153264 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7690. Min Range: -5.7690
Max Act: 5.5503. Min Act: -0.1700
Data Index: 1996600 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7690. Min Range: -5.7690
Max Act: 5.5503. Min Act: -0.1700
Data Index: 6446726 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7690. Min Range: -5.7690
Max Act: 5.4878. Min Act: -0.1700
Data Index: 3860300 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7690. Min Range: -5.7690
Max Act: 5.3940. Min Act: -0.1700
Data Index: 6802351 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7690. Min Range: -5.7690
Max Act: 5.4253. Min Act: -0.1700
Data Index: 4646871 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7690. Min Range: -5.7690
Max Act: 5.3940. Min Act: -0.1700
Data Index: 6926446 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7690. Min Range: -5.7690
Max Act: 5.3628. Min Act: -0.1700
Data Index: 4021602 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7690. Min Range: -5.7690
Max Act: 5.3628. Min Act: -0.1700
Data Index: 6130353 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7690. Min Range: -5.7690
Max Act: 5.3315. Min Act: -0.1700
Data Index: 7922116 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7690. Min Range: -5.7690
Max Act: 5.3315. Min Act: -0.1700
Data Index: 3367058 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7690. Min Range: -5.7690
Max Act: 5.3628. Min Act: -0.1700
Data Index: 8798907 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7690. Min Range: -5.7690
Max Act: 5.3628. Min Act: -0.1700
Data Index: 1979322 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7690. Min Range: -5.7690
Max Act: 5.3315. Min Act: -0.1700
Data Index: 547267 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7690. Min Range: -5.7690
Max Act: 5.3003. Min Act: -0.1700
Data Index: 6204565 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7690. Min Range: -5.7690
Max Act: 5.2690. Min Act: -0.1700
Data Index: 1632915 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19