Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1642 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.2371. Min Act: -0.1698
Data Index: 3378240 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.2058. Min Act: -0.1698
Data Index: 359354 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.2058. Min Act: -0.1700
Data Index: 7569448 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.1746. Min Act: -0.1699
Data Index: 7166490 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.2058. Min Act: -0.1700
Data Index: 5647678 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.2371. Min Act: -0.1700
Data Index: 359347 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.2058. Min Act: -0.1700
Data Index: 4610446 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.2058. Min Act: -0.1700
Data Index: 4532203 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.2058. Min Act: -0.1700
Data Index: 1387250 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.2058. Min Act: -0.1699
Data Index: 823839 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.2058. Min Act: -0.1699
Data Index: 3560762 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.2058. Min Act: -0.1698
Data Index: 2791652 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.2058. Min Act: -0.1700
Data Index: 1671369 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.2058. Min Act: -0.1700
Data Index: 29608 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.1746. Min Act: -0.1700
Data Index: 4313592 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.1746. Min Act: -0.1700
Data Index: 3880197 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.1433. Min Act: -0.1695
Data Index: 2807249 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.1746. Min Act: -0.1700
Data Index: 2312788 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.1746. Min Act: -0.1700
Data Index: 1736700 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.1433. Min Act: -0.1700
Data Index: 555805 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19