Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5244 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9532. Min Range: -3.9532
Max Act: 3.9219. Min Act: -0.1700
Data Index: 8507600 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9532. Min Range: -3.9532
Max Act: 3.9532. Min Act: -0.1700
Data Index: 5268871 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9532. Min Range: -3.9532
Max Act: 3.8594. Min Act: -0.1700
Data Index: 2000285 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9532. Min Range: -3.9532
Max Act: 3.8907. Min Act: -0.1700
Data Index: 4058888 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9532. Min Range: -3.9532
Max Act: 3.7969. Min Act: -0.1700
Data Index: 501149 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9532. Min Range: -3.9532
Max Act: 3.8281. Min Act: -0.1700
Data Index: 773121 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9532. Min Range: -3.9532
Max Act: 3.7969. Min Act: -0.1700
Data Index: 1940923 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9532. Min Range: -3.9532
Max Act: 3.7656. Min Act: -0.1700
Data Index: 4086348 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9532. Min Range: -3.9532
Max Act: 3.7343. Min Act: -0.1700
Data Index: 3709774 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9532. Min Range: -3.9532
Max Act: 3.7187. Min Act: -0.1700
Data Index: 8123814 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9532. Min Range: -3.9532
Max Act: 3.7187. Min Act: -0.1700
Data Index: 3982046 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9532. Min Range: -3.9532
Max Act: 3.7030. Min Act: -0.1700
Data Index: 3212827 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9532. Min Range: -3.9532
Max Act: 3.7187. Min Act: -0.1700
Data Index: 8045526 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9532. Min Range: -3.9532
Max Act: 3.7030. Min Act: -0.1700
Data Index: 1532046 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9532. Min Range: -3.9532
Max Act: 3.7030. Min Act: -0.1700
Data Index: 5285638 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9532. Min Range: -3.9532
Max Act: 3.6874. Min Act: -0.1700
Data Index: 1648612 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9532. Min Range: -3.9532
Max Act: 3.7030. Min Act: -0.1700
Data Index: 8546470 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9532. Min Range: -3.9532
Max Act: 3.6717. Min Act: -0.1700
Data Index: 5354044 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9532. Min Range: -3.9532
Max Act: 3.6874. Min Act: -0.1700
Data Index: 8365086 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9532. Min Range: -3.9532
Max Act: 3.6561. Min Act: -0.1700
Data Index: 7187056 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19