Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2728 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5431. Min Range: -1.5431
Max Act: 1.5431. Min Act: -0.1700
Data Index: 8082882 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5431. Min Range: -1.5431
Max Act: 1.5431. Min Act: -0.1699
Data Index: 7171878 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5431. Min Range: -1.5431
Max Act: 1.4904. Min Act: -0.1699
Data Index: 129763 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5431. Min Range: -1.5431
Max Act: 1.4816. Min Act: -0.1700
Data Index: 4259068 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5431. Min Range: -1.5431
Max Act: 1.4816. Min Act: -0.1700
Data Index: 6680284 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5431. Min Range: -1.5431
Max Act: 1.4816. Min Act: -0.1697
Data Index: 1323525 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5431. Min Range: -1.5431
Max Act: 1.4729. Min Act: -0.1700
Data Index: 1065296 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5431. Min Range: -1.5431
Max Act: 1.4641. Min Act: -0.1700
Data Index: 6577476 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5431. Min Range: -1.5431
Max Act: 1.4641. Min Act: -0.1695
Data Index: 7877176 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5431. Min Range: -1.5431
Max Act: 1.4465. Min Act: -0.1700
Data Index: 7766573 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5431. Min Range: -1.5431
Max Act: 1.4641. Min Act: -0.1700
Data Index: 2197971 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5431. Min Range: -1.5431
Max Act: 1.4641. Min Act: -0.1700
Data Index: 4026095 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5431. Min Range: -1.5431
Max Act: 1.4553. Min Act: -0.1700
Data Index: 6748581 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5431. Min Range: -1.5431
Max Act: 1.4553. Min Act: -0.1700
Data Index: 6759024 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5431. Min Range: -1.5431
Max Act: 1.4465. Min Act: -0.1691
Data Index: 2441120 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5431. Min Range: -1.5431
Max Act: 1.4465. Min Act: -0.1700
Data Index: 3864056 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5431. Min Range: -1.5431
Max Act: 1.4377. Min Act: -0.1699
Data Index: 5112524 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5431. Min Range: -1.5431
Max Act: 1.4465. Min Act: -0.1700
Data Index: 6284283 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5431. Min Range: -1.5431
Max Act: 1.4465. Min Act: -0.1700
Data Index: 177944 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5431. Min Range: -1.5431
Max Act: 1.4377. Min Act: -0.1700
Data Index: 5134577 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #19