Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4040 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8103. Min Range: -4.8103
Max Act: 4.8103. Min Act: -0.1700
Data Index: 7981720 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8103. Min Range: -4.8103
Max Act: 4.5603. Min Act: -0.1700
Data Index: 6128784 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8103. Min Range: -4.8103
Max Act: 4.5603. Min Act: -0.1700
Data Index: 312154 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8103. Min Range: -4.8103
Max Act: 4.5603. Min Act: -0.1700
Data Index: 2312749 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8103. Min Range: -4.8103
Max Act: 4.5291. Min Act: -0.1700
Data Index: 7894285 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8103. Min Range: -4.8103
Max Act: 4.5291. Min Act: -0.1700
Data Index: 6021318 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8103. Min Range: -4.8103
Max Act: 4.5291. Min Act: -0.1700
Data Index: 844200 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8103. Min Range: -4.8103
Max Act: 4.4978. Min Act: -0.1700
Data Index: 7371461 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8103. Min Range: -4.8103
Max Act: 4.4666. Min Act: -0.1700
Data Index: 3193997 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8103. Min Range: -4.8103
Max Act: 4.4666. Min Act: -0.1700
Data Index: 5300770 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8103. Min Range: -4.8103
Max Act: 4.4666. Min Act: -0.1700
Data Index: 3153172 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8103. Min Range: -4.8103
Max Act: 4.4666. Min Act: -0.1700
Data Index: 2173410 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8103. Min Range: -4.8103
Max Act: 4.4353. Min Act: -0.1700
Data Index: 3086535 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8103. Min Range: -4.8103
Max Act: 4.4666. Min Act: -0.1700
Data Index: 7098128 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8103. Min Range: -4.8103
Max Act: 4.4353. Min Act: -0.1700
Data Index: 2656396 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8103. Min Range: -4.8103
Max Act: 4.4353. Min Act: -0.1700
Data Index: 1570088 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8103. Min Range: -4.8103
Max Act: 4.4041. Min Act: -0.1700
Data Index: 5439591 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8103. Min Range: -4.8103
Max Act: 4.4041. Min Act: -0.1700
Data Index: 2421384 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8103. Min Range: -4.8103
Max Act: 4.3728. Min Act: -0.1700
Data Index: 2244475 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8103. Min Range: -4.8103
Max Act: 4.3728. Min Act: -0.1700
Data Index: 5720648 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19