Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3132 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3610. Min Range: -6.3610
Max Act: 6.3610. Min Act: -0.1700
Data Index: 4319552 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3610. Min Range: -6.3610
Max Act: 6.3610. Min Act: -0.1700
Data Index: 250347 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3610. Min Range: -6.3610
Max Act: 6.2985. Min Act: -0.1700
Data Index: 6542938 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3610. Min Range: -6.3610
Max Act: 6.3298. Min Act: -0.1700
Data Index: 5455158 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3610. Min Range: -6.3610
Max Act: 6.2360. Min Act: -0.1700
Data Index: 664808 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3610. Min Range: -6.3610
Max Act: 6.2048. Min Act: -0.1700
Data Index: 4006186 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3610. Min Range: -6.3610
Max Act: 6.1735. Min Act: -0.1700
Data Index: 2235580 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3610. Min Range: -6.3610
Max Act: 6.1110. Min Act: -0.1700
Data Index: 2139296 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3610. Min Range: -6.3610
Max Act: 6.1110. Min Act: -0.1700
Data Index: 6074836 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3610. Min Range: -6.3610
Max Act: 6.1110. Min Act: -0.1700
Data Index: 472175 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3610. Min Range: -6.3610
Max Act: 6.0485. Min Act: -0.1700
Data Index: 1011826 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3610. Min Range: -6.3610
Max Act: 6.0173. Min Act: -0.1700
Data Index: 4921575 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3610. Min Range: -6.3610
Max Act: 6.0173. Min Act: -0.1700
Data Index: 8626567 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3610. Min Range: -6.3610
Max Act: 5.9548. Min Act: -0.1700
Data Index: 7586642 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3610. Min Range: -6.3610
Max Act: 5.9548. Min Act: -0.1700
Data Index: 585401 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3610. Min Range: -6.3610
Max Act: 5.9235. Min Act: -0.1700
Data Index: 6786121 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3610. Min Range: -6.3610
Max Act: 5.9235. Min Act: -0.1700
Data Index: 4644784 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3610. Min Range: -6.3610
Max Act: 5.9235. Min Act: -0.1700
Data Index: 3446367 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3610. Min Range: -6.3610
Max Act: 5.8923. Min Act: -0.1700
Data Index: 4520124 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3610. Min Range: -6.3610
Max Act: 5.8923. Min Act: -0.1700
Data Index: 3383718 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19