Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2538 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.2453. Min Act: -0.1435
Data Index: 6502230 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.0891. Min Act: -0.1664
Data Index: 1553625 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.0891. Min Act: -0.1634
Data Index: 2672914 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.0266. Min Act: -0.1676
Data Index: 1917968 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2453. Min Range: -4.2453
Max Act: 3.9953. Min Act: -0.1694
Data Index: 7389495 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2453. Min Range: -4.2453
Max Act: 3.9640. Min Act: -0.1700
Data Index: 6171212 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2453. Min Range: -4.2453
Max Act: 3.9640. Min Act: -0.1699
Data Index: 2678334 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2453. Min Range: -4.2453
Max Act: 3.9640. Min Act: -0.1700
Data Index: 4948587 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2453. Min Range: -4.2453
Max Act: 3.9328. Min Act: -0.1687
Data Index: 5591036 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2453. Min Range: -4.2453
Max Act: 3.9328. Min Act: -0.1341
Data Index: 7175528 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2453. Min Range: -4.2453
Max Act: 3.9640. Min Act: -0.1700
Data Index: 8439533 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2453. Min Range: -4.2453
Max Act: 3.9015. Min Act: -0.1587
Data Index: 4487581 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2453. Min Range: -4.2453
Max Act: 3.9015. Min Act: -0.1700
Data Index: 512434 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2453. Min Range: -4.2453
Max Act: 3.9015. Min Act: -0.1696
Data Index: 3910120 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2453. Min Range: -4.2453
Max Act: 3.9015. Min Act: -0.1700
Data Index: 7978436 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2453. Min Range: -4.2453
Max Act: 3.8702. Min Act: -0.1700
Data Index: 1917962 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2453. Min Range: -4.2453
Max Act: 3.8702. Min Act: -0.1700
Data Index: 3991400 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2453. Min Range: -4.2453
Max Act: 3.8702. Min Act: -0.1697
Data Index: 2158004 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2453. Min Range: -4.2453
Max Act: 3.8390. Min Act: -0.1692
Data Index: 7518669 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2453. Min Range: -4.2453
Max Act: 3.8702. Min Act: -0.1690
Data Index: 6800894 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #19