Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1781 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6909. Min Range: -4.6909
Max Act: 4.6909. Min Act: -0.1700
Data Index: 7149103 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6909. Min Range: -4.6909
Max Act: 4.6909. Min Act: -0.1700
Data Index: 178197 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6909. Min Range: -4.6909
Max Act: 4.5659. Min Act: -0.1700
Data Index: 3965750 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6909. Min Range: -4.6909
Max Act: 4.5347. Min Act: -0.1700
Data Index: 3431425 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6909. Min Range: -4.6909
Max Act: 4.5034. Min Act: -0.1700
Data Index: 8134161 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6909. Min Range: -4.6909
Max Act: 4.4722. Min Act: -0.1700
Data Index: 1314626 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6909. Min Range: -4.6909
Max Act: 4.4722. Min Act: -0.1700
Data Index: 6494332 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6909. Min Range: -4.6909
Max Act: 4.4409. Min Act: -0.1700
Data Index: 4650055 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6909. Min Range: -4.6909
Max Act: 4.4409. Min Act: -0.1700
Data Index: 8463794 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6909. Min Range: -4.6909
Max Act: 4.4097. Min Act: -0.1700
Data Index: 2593043 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6909. Min Range: -4.6909
Max Act: 4.4409. Min Act: -0.1700
Data Index: 5822591 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6909. Min Range: -4.6909
Max Act: 4.4097. Min Act: -0.1700
Data Index: 4904891 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6909. Min Range: -4.6909
Max Act: 4.4097. Min Act: -0.1700
Data Index: 6163087 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6909. Min Range: -4.6909
Max Act: 4.4097. Min Act: -0.1700
Data Index: 7495893 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6909. Min Range: -4.6909
Max Act: 4.4097. Min Act: -0.1700
Data Index: 6691707 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6909. Min Range: -4.6909
Max Act: 4.4097. Min Act: -0.1700
Data Index: 7483745 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6909. Min Range: -4.6909
Max Act: 4.4097. Min Act: -0.1700
Data Index: 3735282 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6909. Min Range: -4.6909
Max Act: 4.4097. Min Act: -0.1700
Data Index: 4495802 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6909. Min Range: -4.6909
Max Act: 4.4097. Min Act: -0.1700
Data Index: 5564437 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6909. Min Range: -4.6909
Max Act: 4.3784. Min Act: -0.1700
Data Index: 2333425 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #19