Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2758 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3859. Min Range: -8.3859
Max Act: 8.3859. Min Act: -0.1700
Data Index: 4806472 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3859. Min Range: -8.3859
Max Act: 8.1359. Min Act: -0.1700
Data Index: 3317240 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3859. Min Range: -8.3859
Max Act: 8.0734. Min Act: -0.1700
Data Index: 7249872 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3859. Min Range: -8.3859
Max Act: 7.9484. Min Act: -0.1700
Data Index: 3461361 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3859. Min Range: -8.3859
Max Act: 7.8546. Min Act: -0.1700
Data Index: 3835504 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3859. Min Range: -8.3859
Max Act: 7.7609. Min Act: -0.1700
Data Index: 6424585 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3859. Min Range: -8.3859
Max Act: 7.7296. Min Act: -0.1700
Data Index: 1004835 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3859. Min Range: -8.3859
Max Act: 7.6671. Min Act: -0.1700
Data Index: 6424604 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3859. Min Range: -8.3859
Max Act: 7.6359. Min Act: -0.1700
Data Index: 8388809 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3859. Min Range: -8.3859
Max Act: 7.6359. Min Act: -0.1700
Data Index: 3999875 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3859. Min Range: -8.3859
Max Act: 7.6046. Min Act: -0.1700
Data Index: 4527176 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3859. Min Range: -8.3859
Max Act: 7.6046. Min Act: -0.1700
Data Index: 3370832 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3859. Min Range: -8.3859
Max Act: 7.5734. Min Act: -0.1700
Data Index: 2306668 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3859. Min Range: -8.3859
Max Act: 7.5421. Min Act: -0.1700
Data Index: 894481 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3859. Min Range: -8.3859
Max Act: 7.5734. Min Act: -0.1700
Data Index: 852862 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3859. Min Range: -8.3859
Max Act: 7.5421. Min Act: -0.1700
Data Index: 2641871 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3859. Min Range: -8.3859
Max Act: 7.5421. Min Act: -0.1700
Data Index: 5093485 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3859. Min Range: -8.3859
Max Act: 7.5421. Min Act: -0.1700
Data Index: 5768164 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3859. Min Range: -8.3859
Max Act: 7.4796. Min Act: -0.1700
Data Index: 1061799 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3859. Min Range: -8.3859
Max Act: 7.4796. Min Act: -0.1700
Data Index: 5605070 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19