Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1199 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6898. Min Range: -6.6898
Max Act: 6.6898. Min Act: -0.1700
Data Index: 8574720 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6898. Min Range: -6.6898
Max Act: 6.1898. Min Act: -0.1700
Data Index: 2960344 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6898. Min Range: -6.6898
Max Act: 6.1898. Min Act: -0.1700
Data Index: 2060152 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6898. Min Range: -6.6898
Max Act: 6.1586. Min Act: -0.1700
Data Index: 8297289 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6898. Min Range: -6.6898
Max Act: 6.1273. Min Act: -0.1700
Data Index: 1651389 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6898. Min Range: -6.6898
Max Act: 6.0961. Min Act: -0.1700
Data Index: 2917517 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6898. Min Range: -6.6898
Max Act: 6.0648. Min Act: -0.1700
Data Index: 4951680 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6898. Min Range: -6.6898
Max Act: 6.0336. Min Act: -0.1700
Data Index: 5686907 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6898. Min Range: -6.6898
Max Act: 6.0336. Min Act: -0.1700
Data Index: 2337152 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6898. Min Range: -6.6898
Max Act: 6.0023. Min Act: -0.1700
Data Index: 3587556 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6898. Min Range: -6.6898
Max Act: 6.0023. Min Act: -0.1700
Data Index: 2178897 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6898. Min Range: -6.6898
Max Act: 6.0023. Min Act: -0.1700
Data Index: 2243680 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6898. Min Range: -6.6898
Max Act: 5.9711. Min Act: -0.1700
Data Index: 7277906 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6898. Min Range: -6.6898
Max Act: 5.9086. Min Act: -0.1700
Data Index: 4568494 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6898. Min Range: -6.6898
Max Act: 5.8773. Min Act: -0.1700
Data Index: 3904476 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6898. Min Range: -6.6898
Max Act: 5.8773. Min Act: -0.1700
Data Index: 3958774 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6898. Min Range: -6.6898
Max Act: 5.8773. Min Act: -0.1700
Data Index: 150182 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6898. Min Range: -6.6898
Max Act: 5.8148. Min Act: -0.1700
Data Index: 5968658 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6898. Min Range: -6.6898
Max Act: 5.7836. Min Act: -0.1700
Data Index: 908808 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6898. Min Range: -6.6898
Max Act: 5.7836. Min Act: -0.1700
Data Index: 6664879 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19