Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1393 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.5874. Min Range: -13.5874
Max Act: 13.5874. Min Act: -0.1700
Data Index: 842835 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.5874. Min Range: -13.5874
Max Act: 13.4624. Min Act: -0.1700
Data Index: 7531315 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.5874. Min Range: -13.5874
Max Act: 13.3999. Min Act: -0.1700
Data Index: 6981263 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.5874. Min Range: -13.5874
Max Act: 13.4624. Min Act: -0.1700
Data Index: 1550477 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.5874. Min Range: -13.5874
Max Act: 13.3374. Min Act: -0.1700
Data Index: 7970954 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.5874. Min Range: -13.5874
Max Act: 13.2749. Min Act: -0.1700
Data Index: 4551979 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.5874. Min Range: -13.5874
Max Act: 13.2749. Min Act: -0.1700
Data Index: 842839 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.5874. Min Range: -13.5874
Max Act: 13.3374. Min Act: -0.1700
Data Index: 6405826 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.5874. Min Range: -13.5874
Max Act: 13.3374. Min Act: -0.1700
Data Index: 5770932 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.5874. Min Range: -13.5874
Max Act: 13.3374. Min Act: -0.1700
Data Index: 6338253 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.5874. Min Range: -13.5874
Max Act: 13.2749. Min Act: -0.1700
Data Index: 2827851 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.5874. Min Range: -13.5874
Max Act: 13.2124. Min Act: -0.1700
Data Index: 7629266 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.5874. Min Range: -13.5874
Max Act: 13.2749. Min Act: -0.1700
Data Index: 3085925 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.5874. Min Range: -13.5874
Max Act: 13.2124. Min Act: -0.1700
Data Index: 7629263 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.5874. Min Range: -13.5874
Max Act: 13.2124. Min Act: -0.1700
Data Index: 6109831 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.5874. Min Range: -13.5874
Max Act: 13.2124. Min Act: -0.1700
Data Index: 6190339 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.5874. Min Range: -13.5874
Max Act: 13.2124. Min Act: -0.1700
Data Index: 7629257 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.5874. Min Range: -13.5874
Max Act: 13.1499. Min Act: -0.1700
Data Index: 1678570 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.5874. Min Range: -13.5874
Max Act: 13.1499. Min Act: -0.1700
Data Index: 1315727 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.5874. Min Range: -13.5874
Max Act: 13.1499. Min Act: -0.1700
Data Index: 5791217 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #19