Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1911 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3390. Min Range: -6.3390
Max Act: 6.3390. Min Act: -0.1700
Data Index: 5402827 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3390. Min Range: -6.3390
Max Act: 6.3078. Min Act: -0.1700
Data Index: 6094085 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3390. Min Range: -6.3390
Max Act: 6.0890. Min Act: -0.1700
Data Index: 8371071 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3390. Min Range: -6.3390
Max Act: 6.0578. Min Act: -0.1700
Data Index: 3703601 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3390. Min Range: -6.3390
Max Act: 6.0578. Min Act: -0.1700
Data Index: 3397331 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3390. Min Range: -6.3390
Max Act: 5.9953. Min Act: -0.1700
Data Index: 1241394 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3390. Min Range: -6.3390
Max Act: 5.9640. Min Act: -0.1700
Data Index: 1311752 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3390. Min Range: -6.3390
Max Act: 5.9640. Min Act: -0.1700
Data Index: 2048598 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3390. Min Range: -6.3390
Max Act: 5.9640. Min Act: -0.1700
Data Index: 5346549 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3390. Min Range: -6.3390
Max Act: 5.9640. Min Act: -0.1700
Data Index: 7205982 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3390. Min Range: -6.3390
Max Act: 5.9328. Min Act: -0.1700
Data Index: 6335046 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3390. Min Range: -6.3390
Max Act: 5.9328. Min Act: -0.1700
Data Index: 1790816 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3390. Min Range: -6.3390
Max Act: 5.9015. Min Act: -0.1700
Data Index: 3682979 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3390. Min Range: -6.3390
Max Act: 5.9015. Min Act: -0.1700
Data Index: 395198 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3390. Min Range: -6.3390
Max Act: 5.8703. Min Act: -0.1700
Data Index: 459719 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3390. Min Range: -6.3390
Max Act: 5.9328. Min Act: -0.1700
Data Index: 4781120 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3390. Min Range: -6.3390
Max Act: 5.9015. Min Act: -0.1700
Data Index: 1349064 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3390. Min Range: -6.3390
Max Act: 5.9015. Min Act: -0.1700
Data Index: 4431127 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3390. Min Range: -6.3390
Max Act: 5.9015. Min Act: -0.1700
Data Index: 3199869 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3390. Min Range: -6.3390
Max Act: 5.8703. Min Act: -0.1700
Data Index: 5626663 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19