Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 524 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7851. Min Range: -5.7851
Max Act: 5.7851. Min Act: -0.1700
Data Index: 5097369 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7851. Min Range: -5.7851
Max Act: 5.6913. Min Act: -0.1700
Data Index: 5418673 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7851. Min Range: -5.7851
Max Act: 5.5351. Min Act: -0.1700
Data Index: 1935919 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7851. Min Range: -5.7851
Max Act: 5.5038. Min Act: -0.1700
Data Index: 4440450 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7851. Min Range: -5.7851
Max Act: 5.4726. Min Act: -0.1700
Data Index: 5852986 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7851. Min Range: -5.7851
Max Act: 5.4726. Min Act: -0.1700
Data Index: 491046 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7851. Min Range: -5.7851
Max Act: 5.4413. Min Act: -0.1700
Data Index: 2815067 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7851. Min Range: -5.7851
Max Act: 5.4413. Min Act: -0.1700
Data Index: 6885989 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7851. Min Range: -5.7851
Max Act: 5.4101. Min Act: -0.1700
Data Index: 8263761 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7851. Min Range: -5.7851
Max Act: 5.4101. Min Act: -0.1700
Data Index: 6323959 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7851. Min Range: -5.7851
Max Act: 5.4101. Min Act: -0.1700
Data Index: 2713793 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7851. Min Range: -5.7851
Max Act: 5.3788. Min Act: -0.1700
Data Index: 3974795 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7851. Min Range: -5.7851
Max Act: 5.3163. Min Act: -0.1700
Data Index: 8716056 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7851. Min Range: -5.7851
Max Act: 5.3163. Min Act: -0.1700
Data Index: 83537 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7851. Min Range: -5.7851
Max Act: 5.3163. Min Act: -0.1700
Data Index: 2563587 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7851. Min Range: -5.7851
Max Act: 5.2851. Min Act: -0.1700
Data Index: 2556575 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7851. Min Range: -5.7851
Max Act: 5.2851. Min Act: -0.1700
Data Index: 3684920 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7851. Min Range: -5.7851
Max Act: 5.2538. Min Act: -0.1700
Data Index: 2623558 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7851. Min Range: -5.7851
Max Act: 5.2538. Min Act: -0.1700
Data Index: 6986059 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7851. Min Range: -5.7851
Max Act: 5.1913. Min Act: -0.1700
Data Index: 6892013 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19