Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4928 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5931. Min Range: -5.5931
Max Act: 5.5931. Min Act: -0.1700
Data Index: 1848032 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5931. Min Range: -5.5931
Max Act: 5.4993. Min Act: -0.1700
Data Index: 3316914 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5931. Min Range: -5.5931
Max Act: 5.4993. Min Act: -0.1700
Data Index: 3458945 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5931. Min Range: -5.5931
Max Act: 5.4368. Min Act: -0.1700
Data Index: 3362763 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5931. Min Range: -5.5931
Max Act: 5.4368. Min Act: -0.1700
Data Index: 4919079 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5931. Min Range: -5.5931
Max Act: 5.3743. Min Act: -0.1700
Data Index: 5245840 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5931. Min Range: -5.5931
Max Act: 5.3431. Min Act: -0.1700
Data Index: 382476 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5931. Min Range: -5.5931
Max Act: 5.3431. Min Act: -0.1700
Data Index: 2441868 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5931. Min Range: -5.5931
Max Act: 5.2806. Min Act: -0.1700
Data Index: 5927858 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5931. Min Range: -5.5931
Max Act: 5.2806. Min Act: -0.1700
Data Index: 6241854 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5931. Min Range: -5.5931
Max Act: 5.2181. Min Act: -0.1700
Data Index: 378645 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5931. Min Range: -5.5931
Max Act: 5.2181. Min Act: -0.1700
Data Index: 8624596 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5931. Min Range: -5.5931
Max Act: 5.1868. Min Act: -0.1700
Data Index: 5188861 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5931. Min Range: -5.5931
Max Act: 5.1243. Min Act: -0.1700
Data Index: 4792262 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5931. Min Range: -5.5931
Max Act: 5.0931. Min Act: -0.1700
Data Index: 358527 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5931. Min Range: -5.5931
Max Act: 5.1243. Min Act: -0.1700
Data Index: 3458940 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5931. Min Range: -5.5931
Max Act: 5.1243. Min Act: -0.1700
Data Index: 1848034 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5931. Min Range: -5.5931
Max Act: 5.0931. Min Act: -0.1700
Data Index: 3458939 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5931. Min Range: -5.5931
Max Act: 5.0931. Min Act: -0.1700
Data Index: 6714855 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5931. Min Range: -5.5931
Max Act: 5.0618. Min Act: -0.1700
Data Index: 5927860 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19