Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4241 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0086. Min Range: -7.0086
Max Act: 7.0086. Min Act: -0.1700
Data Index: 5895723 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0086. Min Range: -7.0086
Max Act: 6.8523. Min Act: -0.1700
Data Index: 5908545 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0086. Min Range: -7.0086
Max Act: 6.6648. Min Act: -0.1700
Data Index: 7085444 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0086. Min Range: -7.0086
Max Act: 6.3836. Min Act: -0.1700
Data Index: 257366 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0086. Min Range: -7.0086
Max Act: 6.3523. Min Act: -0.1700
Data Index: 1365505 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0086. Min Range: -7.0086
Max Act: 6.3523. Min Act: -0.1700
Data Index: 5620470 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0086. Min Range: -7.0086
Max Act: 6.3211. Min Act: -0.1700
Data Index: 1589238 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0086. Min Range: -7.0086
Max Act: 6.3211. Min Act: -0.1700
Data Index: 370520 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0086. Min Range: -7.0086
Max Act: 6.3211. Min Act: -0.1700
Data Index: 6683101 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0086. Min Range: -7.0086
Max Act: 6.2898. Min Act: -0.1700
Data Index: 5319294 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0086. Min Range: -7.0086
Max Act: 6.2586. Min Act: -0.1700
Data Index: 3850525 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0086. Min Range: -7.0086
Max Act: 6.2586. Min Act: -0.1700
Data Index: 1978917 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0086. Min Range: -7.0086
Max Act: 6.2586. Min Act: -0.1700
Data Index: 8154639 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0086. Min Range: -7.0086
Max Act: 6.1961. Min Act: -0.1700
Data Index: 5804150 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0086. Min Range: -7.0086
Max Act: 6.1961. Min Act: -0.1700
Data Index: 1609237 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0086. Min Range: -7.0086
Max Act: 6.1961. Min Act: -0.1700
Data Index: 1947474 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0086. Min Range: -7.0086
Max Act: 6.1648. Min Act: -0.1700
Data Index: 8294568 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0086. Min Range: -7.0086
Max Act: 6.1648. Min Act: -0.1700
Data Index: 3744508 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0086. Min Range: -7.0086
Max Act: 6.1648. Min Act: -0.1700
Data Index: 2628427 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0086. Min Range: -7.0086
Max Act: 6.1336. Min Act: -0.1700
Data Index: 5781038 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19