Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2917 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2174. Min Range: -5.2174
Max Act: 5.2174. Min Act: -0.1700
Data Index: 7691000 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2174. Min Range: -5.2174
Max Act: 4.9361. Min Act: -0.1700
Data Index: 3738634 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2174. Min Range: -5.2174
Max Act: 4.9049. Min Act: -0.1700
Data Index: 607914 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2174. Min Range: -5.2174
Max Act: 4.8736. Min Act: -0.1700
Data Index: 215563 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2174. Min Range: -5.2174
Max Act: 4.8736. Min Act: -0.1700
Data Index: 320212 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2174. Min Range: -5.2174
Max Act: 4.8111. Min Act: -0.1700
Data Index: 2053374 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2174. Min Range: -5.2174
Max Act: 4.8111. Min Act: -0.1700
Data Index: 7795396 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2174. Min Range: -5.2174
Max Act: 4.7799. Min Act: -0.1700
Data Index: 4832264 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2174. Min Range: -5.2174
Max Act: 4.7486. Min Act: -0.1700
Data Index: 6821388 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2174. Min Range: -5.2174
Max Act: 4.7799. Min Act: -0.1700
Data Index: 6479303 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2174. Min Range: -5.2174
Max Act: 4.7486. Min Act: -0.1700
Data Index: 6040316 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2174. Min Range: -5.2174
Max Act: 4.7174. Min Act: -0.1700
Data Index: 2289942 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2174. Min Range: -5.2174
Max Act: 4.7174. Min Act: -0.1700
Data Index: 3585728 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2174. Min Range: -5.2174
Max Act: 4.6549. Min Act: -0.1700
Data Index: 6083876 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2174. Min Range: -5.2174
Max Act: 4.6861. Min Act: -0.1700
Data Index: 503555 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2174. Min Range: -5.2174
Max Act: 4.6861. Min Act: -0.1700
Data Index: 1551624 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2174. Min Range: -5.2174
Max Act: 4.6861. Min Act: -0.1700
Data Index: 3537533 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2174. Min Range: -5.2174
Max Act: 4.6549. Min Act: -0.1700
Data Index: 3738640 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2174. Min Range: -5.2174
Max Act: 4.6861. Min Act: -0.1700
Data Index: 1946565 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2174. Min Range: -5.2174
Max Act: 4.6861. Min Act: -0.1700
Data Index: 7964679 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19