Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1981 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5674. Min Range: -4.5674
Max Act: 4.5674. Min Act: -0.1700
Data Index: 7141082 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5674. Min Range: -4.5674
Max Act: 4.5674. Min Act: -0.1700
Data Index: 4438106 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5674. Min Range: -4.5674
Max Act: 4.5049. Min Act: -0.1700
Data Index: 4748963 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5674. Min Range: -4.5674
Max Act: 4.4736. Min Act: -0.1700
Data Index: 1320068 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5674. Min Range: -4.5674
Max Act: 4.4736. Min Act: -0.1700
Data Index: 4501501 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5674. Min Range: -4.5674
Max Act: 4.4736. Min Act: -0.1700
Data Index: 1224311 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5674. Min Range: -4.5674
Max Act: 4.4736. Min Act: -0.1700
Data Index: 7854810 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5674. Min Range: -4.5674
Max Act: 4.4424. Min Act: -0.1700
Data Index: 4406684 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5674. Min Range: -4.5674
Max Act: 4.4424. Min Act: -0.1700
Data Index: 1555370 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5674. Min Range: -4.5674
Max Act: 4.4424. Min Act: -0.1700
Data Index: 5737202 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5674. Min Range: -4.5674
Max Act: 4.4111. Min Act: -0.1700
Data Index: 5646297 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5674. Min Range: -4.5674
Max Act: 4.4111. Min Act: -0.1700
Data Index: 1320069 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5674. Min Range: -4.5674
Max Act: 4.4111. Min Act: -0.1700
Data Index: 7217443 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5674. Min Range: -4.5674
Max Act: 4.4111. Min Act: -0.1700
Data Index: 8679635 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5674. Min Range: -4.5674
Max Act: 4.4111. Min Act: -0.1700
Data Index: 4402513 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5674. Min Range: -4.5674
Max Act: 4.3799. Min Act: -0.1700
Data Index: 7012023 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5674. Min Range: -4.5674
Max Act: 4.4111. Min Act: -0.1700
Data Index: 7005176 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5674. Min Range: -4.5674
Max Act: 4.3799. Min Act: -0.1700
Data Index: 720337 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5674. Min Range: -4.5674
Max Act: 4.3799. Min Act: -0.1700
Data Index: 3909018 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5674. Min Range: -4.5674
Max Act: 4.3799. Min Act: -0.1700
Data Index: 5435144 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19