Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5815 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9702. Min Range: -8.9702
Max Act: 8.9702. Min Act: -0.1700
Data Index: 1444550 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9702. Min Range: -8.9702
Max Act: 8.8452. Min Act: -0.1700
Data Index: 6900870 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9702. Min Range: -8.9702
Max Act: 8.7827. Min Act: -0.1700
Data Index: 1399544 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9702. Min Range: -8.9702
Max Act: 8.7202. Min Act: -0.1700
Data Index: 409888 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9702. Min Range: -8.9702
Max Act: 8.7202. Min Act: -0.1700
Data Index: 4601793 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9702. Min Range: -8.9702
Max Act: 8.6577. Min Act: -0.1700
Data Index: 7211422 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9702. Min Range: -8.9702
Max Act: 8.6577. Min Act: -0.1700
Data Index: 106339 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9702. Min Range: -8.9702
Max Act: 8.5952. Min Act: -0.1700
Data Index: 7239 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9702. Min Range: -8.9702
Max Act: 8.5327. Min Act: -0.1700
Data Index: 4173692 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9702. Min Range: -8.9702
Max Act: 8.4702. Min Act: -0.1700
Data Index: 7959938 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9702. Min Range: -8.9702
Max Act: 8.4702. Min Act: -0.1700
Data Index: 884608 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9702. Min Range: -8.9702
Max Act: 8.4702. Min Act: -0.1700
Data Index: 6374228 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9702. Min Range: -8.9702
Max Act: 8.4077. Min Act: -0.1696
Data Index: 8020482 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9702. Min Range: -8.9702
Max Act: 8.4077. Min Act: -0.1700
Data Index: 5276582 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9702. Min Range: -8.9702
Max Act: 8.4077. Min Act: -0.1700
Data Index: 6947944 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9702. Min Range: -8.9702
Max Act: 8.4077. Min Act: -0.1700
Data Index: 4966730 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9702. Min Range: -8.9702
Max Act: 8.3452. Min Act: -0.1700
Data Index: 6338578 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9702. Min Range: -8.9702
Max Act: 8.3452. Min Act: -0.1700
Data Index: 6521806 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9702. Min Range: -8.9702
Max Act: 8.3452. Min Act: -0.1700
Data Index: 4447236 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9702. Min Range: -8.9702
Max Act: 8.3452. Min Act: -0.1700
Data Index: 2366147 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #19