Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6355 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0638. Min Range: -7.0638
Max Act: 7.0638. Min Act: -0.1700
Data Index: 7623473 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0638. Min Range: -7.0638
Max Act: 6.9700. Min Act: -0.1700
Data Index: 5441494 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0638. Min Range: -7.0638
Max Act: 6.9075. Min Act: -0.1700
Data Index: 614559 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0638. Min Range: -7.0638
Max Act: 6.8138. Min Act: -0.1700
Data Index: 770671 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0638. Min Range: -7.0638
Max Act: 6.7513. Min Act: -0.1700
Data Index: 4704359 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0638. Min Range: -7.0638
Max Act: 6.7200. Min Act: -0.1700
Data Index: 1570896 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0638. Min Range: -7.0638
Max Act: 6.7200. Min Act: -0.1700
Data Index: 5663470 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0638. Min Range: -7.0638
Max Act: 6.7200. Min Act: -0.1700
Data Index: 7346915 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0638. Min Range: -7.0638
Max Act: 6.6888. Min Act: -0.1700
Data Index: 152094 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0638. Min Range: -7.0638
Max Act: 6.6575. Min Act: -0.1700
Data Index: 5079821 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0638. Min Range: -7.0638
Max Act: 6.6888. Min Act: -0.1700
Data Index: 1211488 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0638. Min Range: -7.0638
Max Act: 6.6575. Min Act: -0.1700
Data Index: 2664788 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0638. Min Range: -7.0638
Max Act: 6.6575. Min Act: -0.1700
Data Index: 5865287 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0638. Min Range: -7.0638
Max Act: 6.6263. Min Act: -0.1700
Data Index: 7430893 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0638. Min Range: -7.0638
Max Act: 6.6263. Min Act: -0.1700
Data Index: 620676 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0638. Min Range: -7.0638
Max Act: 6.5950. Min Act: -0.1700
Data Index: 4738552 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0638. Min Range: -7.0638
Max Act: 6.5325. Min Act: -0.1700
Data Index: 1984912 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0638. Min Range: -7.0638
Max Act: 6.5325. Min Act: -0.1700
Data Index: 3058526 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0638. Min Range: -7.0638
Max Act: 6.5013. Min Act: -0.1700
Data Index: 4995034 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0638. Min Range: -7.0638
Max Act: 6.5013. Min Act: -0.1700
Data Index: 2271335 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19