Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4229 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9591. Min Range: -6.9591
Max Act: 6.9591. Min Act: -0.1700
Data Index: 5086855 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9591. Min Range: -6.9591
Max Act: 6.8341. Min Act: -0.1700
Data Index: 8204028 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9591. Min Range: -6.9591
Max Act: 6.8029. Min Act: -0.1700
Data Index: 1303063 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9591. Min Range: -6.9591
Max Act: 6.7716. Min Act: -0.1700
Data Index: 4538001 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9591. Min Range: -6.9591
Max Act: 6.5841. Min Act: -0.1700
Data Index: 3566057 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9591. Min Range: -6.9591
Max Act: 6.4904. Min Act: -0.1700
Data Index: 1704384 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9591. Min Range: -6.9591
Max Act: 6.4279. Min Act: -0.1700
Data Index: 2725185 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9591. Min Range: -6.9591
Max Act: 6.4279. Min Act: -0.1700
Data Index: 2249797 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9591. Min Range: -6.9591
Max Act: 6.3654. Min Act: -0.1700
Data Index: 6746000 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9591. Min Range: -6.9591
Max Act: 6.3341. Min Act: -0.1700
Data Index: 7313321 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9591. Min Range: -6.9591
Max Act: 6.3029. Min Act: -0.1700
Data Index: 4966806 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9591. Min Range: -6.9591
Max Act: 6.3341. Min Act: -0.1700
Data Index: 7119705 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9591. Min Range: -6.9591
Max Act: 6.2404. Min Act: -0.1700
Data Index: 7673724 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9591. Min Range: -6.9591
Max Act: 6.2404. Min Act: -0.1700
Data Index: 5278973 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9591. Min Range: -6.9591
Max Act: 6.2404. Min Act: -0.1700
Data Index: 179572 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9591. Min Range: -6.9591
Max Act: 6.2404. Min Act: -0.1700
Data Index: 6400674 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9591. Min Range: -6.9591
Max Act: 6.1779. Min Act: -0.1700
Data Index: 2407574 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9591. Min Range: -6.9591
Max Act: 6.2404. Min Act: -0.1700
Data Index: 2974595 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9591. Min Range: -6.9591
Max Act: 6.1779. Min Act: -0.1700
Data Index: 1531804 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9591. Min Range: -6.9591
Max Act: 6.1779. Min Act: -0.1700
Data Index: 5894365 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19