Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4031 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7031. Min Range: -5.7031
Max Act: 5.7031. Min Act: -0.1700
Data Index: 7958103 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7031. Min Range: -5.7031
Max Act: 5.6719. Min Act: -0.1700
Data Index: 8561886 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7031. Min Range: -5.7031
Max Act: 5.3906. Min Act: -0.1700
Data Index: 8721674 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7031. Min Range: -5.7031
Max Act: 5.3594. Min Act: -0.1700
Data Index: 8418847 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7031. Min Range: -5.7031
Max Act: 5.3594. Min Act: -0.1700
Data Index: 5942707 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7031. Min Range: -5.7031
Max Act: 5.2344. Min Act: -0.1700
Data Index: 4108698 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7031. Min Range: -5.7031
Max Act: 5.1719. Min Act: -0.1700
Data Index: 1584793 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7031. Min Range: -5.7031
Max Act: 5.1406. Min Act: -0.1700
Data Index: 4977467 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7031. Min Range: -5.7031
Max Act: 5.1094. Min Act: -0.1700
Data Index: 522661 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7031. Min Range: -5.7031
Max Act: 5.1094. Min Act: -0.1700
Data Index: 293830 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7031. Min Range: -5.7031
Max Act: 5.1094. Min Act: -0.1700
Data Index: 5039067 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7031. Min Range: -5.7031
Max Act: 5.0469. Min Act: -0.1700
Data Index: 6267598 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7031. Min Range: -5.7031
Max Act: 5.0781. Min Act: -0.1700
Data Index: 4650847 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7031. Min Range: -5.7031
Max Act: 5.0781. Min Act: -0.1700
Data Index: 1846106 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7031. Min Range: -5.7031
Max Act: 5.0156. Min Act: -0.1700
Data Index: 3436821 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7031. Min Range: -5.7031
Max Act: 4.9844. Min Act: -0.1700
Data Index: 691146 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7031. Min Range: -5.7031
Max Act: 4.9844. Min Act: -0.1700
Data Index: 4583332 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7031. Min Range: -5.7031
Max Act: 4.9531. Min Act: -0.1700
Data Index: 4796516 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7031. Min Range: -5.7031
Max Act: 4.9531. Min Act: -0.1700
Data Index: 6555445 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7031. Min Range: -5.7031
Max Act: 4.9219. Min Act: -0.1700
Data Index: 421936 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19