Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2175 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4526. Min Range: -6.4526
Max Act: 6.4526. Min Act: -0.1700
Data Index: 6625486 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4526. Min Range: -6.4526
Max Act: 6.1401. Min Act: -0.1700
Data Index: 4674720 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4526. Min Range: -6.4526
Max Act: 6.1088. Min Act: -0.1700
Data Index: 5695764 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4526. Min Range: -6.4526
Max Act: 6.0151. Min Act: -0.1700
Data Index: 6838391 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4526. Min Range: -6.4526
Max Act: 6.0151. Min Act: -0.1700
Data Index: 8448486 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.9838. Min Act: -0.1700
Data Index: 5695762 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.9526. Min Act: -0.1700
Data Index: 3507204 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.9213. Min Act: -0.1700
Data Index: 2005632 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.9213. Min Act: -0.1700
Data Index: 8406437 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.8588. Min Act: -0.1700
Data Index: 3130679 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.8276. Min Act: -0.1700
Data Index: 1289450 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.8276. Min Act: -0.1700
Data Index: 3808652 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.7963. Min Act: -0.1700
Data Index: 3957991 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.7963. Min Act: -0.1700
Data Index: 3861860 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.7651. Min Act: -0.1700
Data Index: 7476444 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.7651. Min Act: -0.1700
Data Index: 2714928 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.7338. Min Act: -0.1700
Data Index: 4050500 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.7338. Min Act: -0.1700
Data Index: 6783746 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.7338. Min Act: -0.1700
Data Index: 4990063 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4526. Min Range: -6.4526
Max Act: 5.7338. Min Act: -0.1700
Data Index: 2237909 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #19