Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1846 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0702. Min Range: -6.0702
Max Act: 6.0702. Min Act: -0.1700
Data Index: 6147465 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0702. Min Range: -6.0702
Max Act: 5.7264. Min Act: -0.1700
Data Index: 5048557 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0702. Min Range: -6.0702
Max Act: 5.7577. Min Act: -0.1700
Data Index: 7671639 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0702. Min Range: -6.0702
Max Act: 5.7264. Min Act: -0.1700
Data Index: 2689885 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0702. Min Range: -6.0702
Max Act: 5.6639. Min Act: -0.1700
Data Index: 8042289 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0702. Min Range: -6.0702
Max Act: 5.6327. Min Act: -0.1700
Data Index: 2746993 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0702. Min Range: -6.0702
Max Act: 5.6327. Min Act: -0.1700
Data Index: 4289851 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0702. Min Range: -6.0702
Max Act: 5.6639. Min Act: -0.1700
Data Index: 5584900 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0702. Min Range: -6.0702
Max Act: 5.6014. Min Act: -0.1700
Data Index: 8774676 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0702. Min Range: -6.0702
Max Act: 5.5702. Min Act: -0.1700
Data Index: 4751219 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0702. Min Range: -6.0702
Max Act: 5.5702. Min Act: -0.1700
Data Index: 6297857 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0702. Min Range: -6.0702
Max Act: 5.5702. Min Act: -0.1700
Data Index: 5684904 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0702. Min Range: -6.0702
Max Act: 5.5702. Min Act: -0.1700
Data Index: 8774678 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0702. Min Range: -6.0702
Max Act: 5.5702. Min Act: -0.1700
Data Index: 602002 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0702. Min Range: -6.0702
Max Act: 5.6014. Min Act: -0.1700
Data Index: 64359 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0702. Min Range: -6.0702
Max Act: 5.5702. Min Act: -0.1700
Data Index: 5266946 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0702. Min Range: -6.0702
Max Act: 5.5389. Min Act: -0.1700
Data Index: 969650 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0702. Min Range: -6.0702
Max Act: 5.5389. Min Act: -0.1700
Data Index: 3141068 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0702. Min Range: -6.0702
Max Act: 5.5389. Min Act: -0.1700
Data Index: 1880388 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0702. Min Range: -6.0702
Max Act: 5.5389. Min Act: -0.1700
Data Index: 8008656 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19