Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3490 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2834. Min Range: -6.2834
Max Act: 6.2834. Min Act: -0.1700
Data Index: 8441020 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2834. Min Range: -6.2834
Max Act: 6.2521. Min Act: -0.1700
Data Index: 1409838 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2834. Min Range: -6.2834
Max Act: 6.2209. Min Act: -0.1700
Data Index: 1444045 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2834. Min Range: -6.2834
Max Act: 6.2209. Min Act: -0.1700
Data Index: 5795542 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2834. Min Range: -6.2834
Max Act: 6.1271. Min Act: -0.1700
Data Index: 5336875 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2834. Min Range: -6.2834
Max Act: 6.0959. Min Act: -0.1700
Data Index: 3920062 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2834. Min Range: -6.2834
Max Act: 6.0646. Min Act: -0.1700
Data Index: 700808 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2834. Min Range: -6.2834
Max Act: 6.0334. Min Act: -0.1700
Data Index: 7042496 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2834. Min Range: -6.2834
Max Act: 6.0334. Min Act: -0.1700
Data Index: 1654828 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2834. Min Range: -6.2834
Max Act: 6.0334. Min Act: -0.1700
Data Index: 5919321 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2834. Min Range: -6.2834
Max Act: 6.0334. Min Act: -0.1700
Data Index: 6214803 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2834. Min Range: -6.2834
Max Act: 6.0334. Min Act: -0.1700
Data Index: 1671117 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2834. Min Range: -6.2834
Max Act: 6.0021. Min Act: -0.1700
Data Index: 5402291 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2834. Min Range: -6.2834
Max Act: 6.0021. Min Act: -0.1700
Data Index: 985348 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2834. Min Range: -6.2834
Max Act: 6.0021. Min Act: -0.1700
Data Index: 6548667 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2834. Min Range: -6.2834
Max Act: 5.9396. Min Act: -0.1700
Data Index: 4920101 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2834. Min Range: -6.2834
Max Act: 5.9709. Min Act: -0.1700
Data Index: 7869772 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2834. Min Range: -6.2834
Max Act: 5.9709. Min Act: -0.1700
Data Index: 2082177 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2834. Min Range: -6.2834
Max Act: 5.9709. Min Act: -0.1700
Data Index: 6752142 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2834. Min Range: -6.2834
Max Act: 5.9709. Min Act: -0.1700
Data Index: 6140319 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19