Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1655 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3023. Min Range: -8.3023
Max Act: 8.3023. Min Act: -0.1700
Data Index: 104566 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3023. Min Range: -8.3023
Max Act: 7.9898. Min Act: -0.1700
Data Index: 1263830 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3023. Min Range: -8.3023
Max Act: 7.9898. Min Act: -0.1700
Data Index: 1852366 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3023. Min Range: -8.3023
Max Act: 7.8648. Min Act: -0.1700
Data Index: 5041414 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3023. Min Range: -8.3023
Max Act: 7.7398. Min Act: -0.1700
Data Index: 4308591 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3023. Min Range: -8.3023
Max Act: 7.5835. Min Act: -0.1700
Data Index: 5574191 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3023. Min Range: -8.3023
Max Act: 7.5835. Min Act: -0.1700
Data Index: 1975224 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3023. Min Range: -8.3023
Max Act: 7.5835. Min Act: -0.1700
Data Index: 5326076 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3023. Min Range: -8.3023
Max Act: 7.5523. Min Act: -0.1700
Data Index: 192549 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3023. Min Range: -8.3023
Max Act: 7.3960. Min Act: -0.1700
Data Index: 8421259 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3023. Min Range: -8.3023
Max Act: 7.3960. Min Act: -0.1700
Data Index: 8101317 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3023. Min Range: -8.3023
Max Act: 7.3960. Min Act: -0.1700
Data Index: 4526979 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3023. Min Range: -8.3023
Max Act: 7.3648. Min Act: -0.1700
Data Index: 7490848 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3023. Min Range: -8.3023
Max Act: 7.3335. Min Act: -0.1700
Data Index: 6409029 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3023. Min Range: -8.3023
Max Act: 7.3335. Min Act: -0.1700
Data Index: 3402375 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3023. Min Range: -8.3023
Max Act: 7.3335. Min Act: -0.1700
Data Index: 154585 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3023. Min Range: -8.3023
Max Act: 7.3023. Min Act: -0.1700
Data Index: 7063822 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3023. Min Range: -8.3023
Max Act: 7.3023. Min Act: -0.1700
Data Index: 5801394 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3023. Min Range: -8.3023
Max Act: 7.2398. Min Act: -0.1700
Data Index: 5726898 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3023. Min Range: -8.3023
Max Act: 7.2710. Min Act: -0.1700
Data Index: 4532236 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #19