Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 313 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4851. Min Range: -5.4851
Max Act: 5.4851. Min Act: -0.1700
Data Index: 3953222 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4851. Min Range: -5.4851
Max Act: 5.4226. Min Act: -0.1700
Data Index: 2728349 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4851. Min Range: -5.4851
Max Act: 5.3601. Min Act: -0.1700
Data Index: 1541108 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4851. Min Range: -5.4851
Max Act: 5.3601. Min Act: -0.1700
Data Index: 7126340 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4851. Min Range: -5.4851
Max Act: 5.3288. Min Act: -0.1700
Data Index: 2629907 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4851. Min Range: -5.4851
Max Act: 5.3288. Min Act: -0.1700
Data Index: 6539979 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4851. Min Range: -5.4851
Max Act: 5.3288. Min Act: -0.1700
Data Index: 950117 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4851. Min Range: -5.4851
Max Act: 5.3288. Min Act: -0.1700
Data Index: 4204250 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4851. Min Range: -5.4851
Max Act: 5.3288. Min Act: -0.1700
Data Index: 7340949 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4851. Min Range: -5.4851
Max Act: 5.3288. Min Act: -0.1700
Data Index: 1132719 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4851. Min Range: -5.4851
Max Act: 5.2976. Min Act: -0.1699
Data Index: 2988506 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4851. Min Range: -5.4851
Max Act: 5.2976. Min Act: -0.1700
Data Index: 4758079 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4851. Min Range: -5.4851
Max Act: 5.2663. Min Act: -0.1700
Data Index: 1598125 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4851. Min Range: -5.4851
Max Act: 5.2976. Min Act: -0.1700
Data Index: 4150663 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4851. Min Range: -5.4851
Max Act: 5.2976. Min Act: -0.1700
Data Index: 7143505 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4851. Min Range: -5.4851
Max Act: 5.2976. Min Act: -0.1700
Data Index: 588367 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4851. Min Range: -5.4851
Max Act: 5.2663. Min Act: -0.1700
Data Index: 539829 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4851. Min Range: -5.4851
Max Act: 5.2663. Min Act: -0.1689
Data Index: 6164272 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4851. Min Range: -5.4851
Max Act: 5.2663. Min Act: -0.1700
Data Index: 6311331 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4851. Min Range: -5.4851
Max Act: 5.2663. Min Act: -0.1700
Data Index: 1997550 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19