Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4617 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6604. Min Range: -4.6604
Max Act: 4.6604. Min Act: -0.1700
Data Index: 953763 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6604. Min Range: -4.6604
Max Act: 4.5979. Min Act: -0.1700
Data Index: 1905231 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6604. Min Range: -4.6604
Max Act: 4.4729. Min Act: -0.1700
Data Index: 810848 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6604. Min Range: -4.6604
Max Act: 4.4729. Min Act: -0.1700
Data Index: 1605508 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6604. Min Range: -4.6604
Max Act: 4.4104. Min Act: -0.1700
Data Index: 1784917 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6604. Min Range: -4.6604
Max Act: 4.3166. Min Act: -0.1700
Data Index: 6903893 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6604. Min Range: -4.6604
Max Act: 4.3166. Min Act: -0.1700
Data Index: 2413249 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6604. Min Range: -4.6604
Max Act: 4.3166. Min Act: -0.1700
Data Index: 6078635 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6604. Min Range: -4.6604
Max Act: 4.2853. Min Act: -0.1700
Data Index: 4919324 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6604. Min Range: -4.6604
Max Act: 4.2853. Min Act: -0.1700
Data Index: 995534 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6604. Min Range: -4.6604
Max Act: 4.2541. Min Act: -0.1700
Data Index: 6795490 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6604. Min Range: -4.6604
Max Act: 4.2228. Min Act: -0.1700
Data Index: 4144551 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6604. Min Range: -4.6604
Max Act: 4.2228. Min Act: -0.1700
Data Index: 415862 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6604. Min Range: -4.6604
Max Act: 4.2228. Min Act: -0.1700
Data Index: 7711222 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6604. Min Range: -4.6604
Max Act: 4.2228. Min Act: -0.1700
Data Index: 3217788 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6604. Min Range: -4.6604
Max Act: 4.1916. Min Act: -0.1700
Data Index: 5443081 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6604. Min Range: -4.6604
Max Act: 4.1916. Min Act: -0.1700
Data Index: 3615331 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6604. Min Range: -4.6604
Max Act: 4.1916. Min Act: -0.1700
Data Index: 1497996 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6604. Min Range: -4.6604
Max Act: 4.1603. Min Act: -0.1700
Data Index: 5725207 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6604. Min Range: -4.6604
Max Act: 4.1603. Min Act: -0.1700
Data Index: 6465781 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19