Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5738 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4300. Min Range: -5.4300
Max Act: 5.4300. Min Act: -0.1700
Data Index: 2876036 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4300. Min Range: -5.4300
Max Act: 5.2738. Min Act: -0.1700
Data Index: 1566142 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4300. Min Range: -5.4300
Max Act: 5.2738. Min Act: -0.1700
Data Index: 7156130 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4300. Min Range: -5.4300
Max Act: 5.2738. Min Act: -0.1700
Data Index: 1490951 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4300. Min Range: -5.4300
Max Act: 5.1488. Min Act: -0.1700
Data Index: 8313771 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4300. Min Range: -5.4300
Max Act: 5.1488. Min Act: -0.1700
Data Index: 3202254 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4300. Min Range: -5.4300
Max Act: 5.1488. Min Act: -0.1700
Data Index: 1412680 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4300. Min Range: -5.4300
Max Act: 5.1175. Min Act: -0.1700
Data Index: 5200463 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4300. Min Range: -5.4300
Max Act: 5.0863. Min Act: -0.1700
Data Index: 104177 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4300. Min Range: -5.4300
Max Act: 5.0863. Min Act: -0.1700
Data Index: 5125216 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4300. Min Range: -5.4300
Max Act: 5.0238. Min Act: -0.1700
Data Index: 606697 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4300. Min Range: -5.4300
Max Act: 5.0550. Min Act: -0.1700
Data Index: 2046047 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4300. Min Range: -5.4300
Max Act: 5.0238. Min Act: -0.1700
Data Index: 5363175 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4300. Min Range: -5.4300
Max Act: 5.0238. Min Act: -0.1700
Data Index: 1906930 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4300. Min Range: -5.4300
Max Act: 5.0238. Min Act: -0.1700
Data Index: 5785219 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4300. Min Range: -5.4300
Max Act: 4.9925. Min Act: -0.1700
Data Index: 7666294 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4300. Min Range: -5.4300
Max Act: 5.0238. Min Act: -0.1700
Data Index: 5356486 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4300. Min Range: -5.4300
Max Act: 5.0238. Min Act: -0.1700
Data Index: 1140 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4300. Min Range: -5.4300
Max Act: 5.0238. Min Act: -0.1700
Data Index: 6524220 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4300. Min Range: -5.4300
Max Act: 4.9925. Min Act: -0.1700
Data Index: 7242583 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19