Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 536 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6129. Min Range: -3.6129
Max Act: 3.6129. Min Act: -0.1700
Data Index: 5592647 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6129. Min Range: -3.6129
Max Act: 3.5033. Min Act: -0.1700
Data Index: 5440901 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6129. Min Range: -3.6129
Max Act: 3.5190. Min Act: -0.1700
Data Index: 6736495 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6129. Min Range: -3.6129
Max Act: 3.4407. Min Act: -0.1700
Data Index: 2408806 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6129. Min Range: -3.6129
Max Act: 3.4407. Min Act: -0.1700
Data Index: 6951993 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6129. Min Range: -3.6129
Max Act: 3.4720. Min Act: -0.1700
Data Index: 3121539 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6129. Min Range: -3.6129
Max Act: 3.4563. Min Act: -0.1700
Data Index: 8110024 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6129. Min Range: -3.6129
Max Act: 3.4563. Min Act: -0.1700
Data Index: 4187922 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6129. Min Range: -3.6129
Max Act: 3.4563. Min Act: -0.1700
Data Index: 4516985 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6129. Min Range: -3.6129
Max Act: 3.4563. Min Act: -0.1700
Data Index: 4027697 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6129. Min Range: -3.6129
Max Act: 3.4720. Min Act: -0.1700
Data Index: 3128351 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6129. Min Range: -3.6129
Max Act: 3.4563. Min Act: -0.1700
Data Index: 8002417 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6129. Min Range: -3.6129
Max Act: 3.4250. Min Act: -0.1700
Data Index: 8504587 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6129. Min Range: -3.6129
Max Act: 3.4407. Min Act: -0.1700
Data Index: 8776383 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6129. Min Range: -3.6129
Max Act: 3.4407. Min Act: -0.1700
Data Index: 2251736 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6129. Min Range: -3.6129
Max Act: 3.4250. Min Act: -0.1700
Data Index: 5669097 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6129. Min Range: -3.6129
Max Act: 3.4093. Min Act: -0.1700
Data Index: 2137339 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6129. Min Range: -3.6129
Max Act: 3.3780. Min Act: -0.1700
Data Index: 3032122 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6129. Min Range: -3.6129
Max Act: 3.4250. Min Act: -0.1700
Data Index: 4414495 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6129. Min Range: -3.6129
Max Act: 3.3780. Min Act: -0.1700
Data Index: 3238528 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19