Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2295 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6828. Min Range: -3.6828
Max Act: 3.6828. Min Act: -0.1700
Data Index: 3151620 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6828. Min Range: -3.6828
Max Act: 3.6671. Min Act: -0.1700
Data Index: 434449 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6828. Min Range: -3.6828
Max Act: 3.6358. Min Act: -0.1700
Data Index: 1785292 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6828. Min Range: -3.6828
Max Act: 3.6045. Min Act: -0.1700
Data Index: 6998182 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6828. Min Range: -3.6828
Max Act: 3.4636. Min Act: -0.1700
Data Index: 948916 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6828. Min Range: -3.6828
Max Act: 3.4323. Min Act: -0.1700
Data Index: 1089850 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6828. Min Range: -3.6828
Max Act: 3.4479. Min Act: -0.1700
Data Index: 8805171 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6828. Min Range: -3.6828
Max Act: 3.4166. Min Act: -0.1700
Data Index: 2523292 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6828. Min Range: -3.6828
Max Act: 3.3852. Min Act: -0.1700
Data Index: 5005092 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6828. Min Range: -3.6828
Max Act: 3.3696. Min Act: -0.1700
Data Index: 7608839 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6828. Min Range: -3.6828
Max Act: 3.3852. Min Act: -0.1700
Data Index: 3123268 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6828. Min Range: -3.6828
Max Act: 3.3696. Min Act: -0.1700
Data Index: 8629335 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6828. Min Range: -3.6828
Max Act: 3.3382. Min Act: -0.1700
Data Index: 4973342 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6828. Min Range: -3.6828
Max Act: 3.2754. Min Act: -0.1700
Data Index: 6509974 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6828. Min Range: -3.6828
Max Act: 3.3068. Min Act: -0.1700
Data Index: 7851047 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6828. Min Range: -3.6828
Max Act: 3.2754. Min Act: -0.1700
Data Index: 167468 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6828. Min Range: -3.6828
Max Act: 3.2911. Min Act: -0.1700
Data Index: 4514067 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6828. Min Range: -3.6828
Max Act: 3.2440. Min Act: -0.1700
Data Index: 6192156 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6828. Min Range: -3.6828
Max Act: 3.2597. Min Act: -0.1700
Data Index: 7566143 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6828. Min Range: -3.6828
Max Act: 3.2597. Min Act: -0.1700
Data Index: 1872809 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19