Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2428 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2021. Min Range: -4.2021
Max Act: 4.2021. Min Act: -0.1700
Data Index: 3366707 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2021. Min Range: -4.2021
Max Act: 4.1083. Min Act: -0.1700
Data Index: 5391309 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2021. Min Range: -4.2021
Max Act: 4.1083. Min Act: -0.1700
Data Index: 3855774 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2021. Min Range: -4.2021
Max Act: 4.1396. Min Act: -0.1700
Data Index: 2698213 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2021. Min Range: -4.2021
Max Act: 4.0771. Min Act: -0.1700
Data Index: 6212158 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2021. Min Range: -4.2021
Max Act: 4.0458. Min Act: -0.1700
Data Index: 2888799 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2021. Min Range: -4.2021
Max Act: 4.0145. Min Act: -0.1700
Data Index: 721592 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2021. Min Range: -4.2021
Max Act: 4.0145. Min Act: -0.1700
Data Index: 6681483 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2021. Min Range: -4.2021
Max Act: 3.9833. Min Act: -0.1700
Data Index: 5581365 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2021. Min Range: -4.2021
Max Act: 3.9208. Min Act: -0.1700
Data Index: 8383324 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2021. Min Range: -4.2021
Max Act: 3.9520. Min Act: -0.1700
Data Index: 2217427 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2021. Min Range: -4.2021
Max Act: 3.8895. Min Act: -0.1700
Data Index: 5686305 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2021. Min Range: -4.2021
Max Act: 3.9208. Min Act: -0.1700
Data Index: 7801514 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2021. Min Range: -4.2021
Max Act: 3.9208. Min Act: -0.1700
Data Index: 1486347 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2021. Min Range: -4.2021
Max Act: 3.9208. Min Act: -0.1700
Data Index: 6568997 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2021. Min Range: -4.2021
Max Act: 3.8895. Min Act: -0.1700
Data Index: 2707911 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2021. Min Range: -4.2021
Max Act: 3.8895. Min Act: -0.1700
Data Index: 2775149 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2021. Min Range: -4.2021
Max Act: 3.9208. Min Act: -0.1700
Data Index: 6772052 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2021. Min Range: -4.2021
Max Act: 3.8895. Min Act: -0.1700
Data Index: 385891 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2021. Min Range: -4.2021
Max Act: 3.8582. Min Act: -0.1700
Data Index: 3571916 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #19