Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 950 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5809. Min Range: -3.5809
Max Act: 3.5809. Min Act: -0.1700
Data Index: 7714617 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5809. Min Range: -3.5809
Max Act: 3.5496. Min Act: -0.1700
Data Index: 4370414 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5809. Min Range: -3.5809
Max Act: 3.5183. Min Act: -0.1700
Data Index: 8591404 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5809. Min Range: -3.5809
Max Act: 3.5183. Min Act: -0.1700
Data Index: 5739906 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5809. Min Range: -3.5809
Max Act: 3.4713. Min Act: -0.1700
Data Index: 642602 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5809. Min Range: -3.5809
Max Act: 3.4713. Min Act: -0.1700
Data Index: 8046240 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5809. Min Range: -3.5809
Max Act: 3.4713. Min Act: -0.1700
Data Index: 4719214 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5809. Min Range: -3.5809
Max Act: 3.4556. Min Act: -0.1700
Data Index: 8001306 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5809. Min Range: -3.5809
Max Act: 3.4400. Min Act: -0.1700
Data Index: 7105356 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5809. Min Range: -3.5809
Max Act: 3.4400. Min Act: -0.1700
Data Index: 7945377 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5809. Min Range: -3.5809
Max Act: 3.4556. Min Act: -0.1700
Data Index: 2077554 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5809. Min Range: -3.5809
Max Act: 3.4243. Min Act: -0.1700
Data Index: 7174003 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5809. Min Range: -3.5809
Max Act: 3.4243. Min Act: -0.1700
Data Index: 7310814 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5809. Min Range: -3.5809
Max Act: 3.4400. Min Act: -0.1700
Data Index: 4622966 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5809. Min Range: -3.5809
Max Act: 3.3929. Min Act: -0.1700
Data Index: 90431 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5809. Min Range: -3.5809
Max Act: 3.4243. Min Act: -0.1700
Data Index: 3855983 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5809. Min Range: -3.5809
Max Act: 3.4400. Min Act: -0.1700
Data Index: 7131128 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5809. Min Range: -3.5809
Max Act: 3.4243. Min Act: -0.1700
Data Index: 6485673 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5809. Min Range: -3.5809
Max Act: 3.4086. Min Act: -0.1700
Data Index: 1789580 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5809. Min Range: -3.5809
Max Act: 3.3929. Min Act: -0.1700
Data Index: 5541172 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19