Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4825 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5284. Min Range: -4.5284
Max Act: 4.5284. Min Act: -0.1700
Data Index: 1168640 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5284. Min Range: -4.5284
Max Act: 4.4034. Min Act: -0.1700
Data Index: 5997771 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5284. Min Range: -4.5284
Max Act: 4.2784. Min Act: -0.1700
Data Index: 3334898 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5284. Min Range: -4.5284
Max Act: 4.2471. Min Act: -0.1700
Data Index: 3627840 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5284. Min Range: -4.5284
Max Act: 4.2159. Min Act: -0.1700
Data Index: 7594566 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5284. Min Range: -4.5284
Max Act: 4.2159. Min Act: -0.1700
Data Index: 8426826 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5284. Min Range: -4.5284
Max Act: 4.2159. Min Act: -0.1700
Data Index: 5492270 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5284. Min Range: -4.5284
Max Act: 4.1533. Min Act: -0.1700
Data Index: 6321015 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5284. Min Range: -4.5284
Max Act: 4.1221. Min Act: -0.1700
Data Index: 5065962 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5284. Min Range: -4.5284
Max Act: 4.1221. Min Act: -0.1700
Data Index: 8072284 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5284. Min Range: -4.5284
Max Act: 4.1533. Min Act: -0.1700
Data Index: 3601063 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5284. Min Range: -4.5284
Max Act: 4.0908. Min Act: -0.1700
Data Index: 6182774 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5284. Min Range: -4.5284
Max Act: 4.0596. Min Act: -0.1700
Data Index: 4891483 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5284. Min Range: -4.5284
Max Act: 4.0596. Min Act: -0.1700
Data Index: 7134660 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5284. Min Range: -4.5284
Max Act: 4.0596. Min Act: -0.1700
Data Index: 7045118 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5284. Min Range: -4.5284
Max Act: 4.0596. Min Act: -0.1700
Data Index: 5736157 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5284. Min Range: -4.5284
Max Act: 4.0596. Min Act: -0.1700
Data Index: 8464102 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5284. Min Range: -4.5284
Max Act: 4.0596. Min Act: -0.1700
Data Index: 3607545 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5284. Min Range: -4.5284
Max Act: 4.0596. Min Act: -0.1700
Data Index: 1354467 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5284. Min Range: -4.5284
Max Act: 4.0596. Min Act: -0.1700
Data Index: 382740 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19