Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4041 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.7812. Min Range: -9.7812
Max Act: 9.7812. Min Act: -0.1700
Data Index: 4428164 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7812. Min Range: -9.7812
Max Act: 9.6562. Min Act: -0.1700
Data Index: 6296609 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7812. Min Range: -9.7812
Max Act: 9.6562. Min Act: -0.1700
Data Index: 3575160 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7812. Min Range: -9.7812
Max Act: 9.6562. Min Act: -0.1700
Data Index: 3723569 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7812. Min Range: -9.7812
Max Act: 9.5937. Min Act: -0.1700
Data Index: 496116 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7812. Min Range: -9.7812
Max Act: 9.5312. Min Act: -0.1700
Data Index: 4095308 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7812. Min Range: -9.7812
Max Act: 9.4687. Min Act: -0.1700
Data Index: 6063637 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7812. Min Range: -9.7812
Max Act: 9.4687. Min Act: -0.1700
Data Index: 3294225 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7812. Min Range: -9.7812
Max Act: 9.4687. Min Act: -0.1700
Data Index: 3711659 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7812. Min Range: -9.7812
Max Act: 9.4687. Min Act: -0.1700
Data Index: 5338033 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7812. Min Range: -9.7812
Max Act: 9.3437. Min Act: -0.1700
Data Index: 4579956 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7812. Min Range: -9.7812
Max Act: 9.3437. Min Act: -0.1700
Data Index: 2638876 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7812. Min Range: -9.7812
Max Act: 9.3437. Min Act: -0.1700
Data Index: 4275726 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7812. Min Range: -9.7812
Max Act: 9.4062. Min Act: -0.1700
Data Index: 4248179 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7812. Min Range: -9.7812
Max Act: 9.4062. Min Act: -0.1700
Data Index: 1201389 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7812. Min Range: -9.7812
Max Act: 9.4062. Min Act: -0.1700
Data Index: 1850461 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7812. Min Range: -9.7812
Max Act: 9.3437. Min Act: -0.1700
Data Index: 1751013 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7812. Min Range: -9.7812
Max Act: 9.4062. Min Act: -0.1700
Data Index: 1697064 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7812. Min Range: -9.7812
Max Act: 9.4062. Min Act: -0.1700
Data Index: 332348 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7812. Min Range: -9.7812
Max Act: 9.3437. Min Act: -0.1700
Data Index: 915196 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19