Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 78 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5588. Min Range: -5.5588
Max Act: 5.5588. Min Act: -0.1700
Data Index: 4290423 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5588. Min Range: -5.5588
Max Act: 5.4651. Min Act: -0.1700
Data Index: 5752442 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5588. Min Range: -5.5588
Max Act: 5.4651. Min Act: -0.1700
Data Index: 8397858 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5588. Min Range: -5.5588
Max Act: 5.4026. Min Act: -0.1700
Data Index: 8044768 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5588. Min Range: -5.5588
Max Act: 5.4026. Min Act: -0.1700
Data Index: 705598 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5588. Min Range: -5.5588
Max Act: 5.3401. Min Act: -0.1700
Data Index: 2590581 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5588. Min Range: -5.5588
Max Act: 5.3088. Min Act: -0.1700
Data Index: 2704503 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5588. Min Range: -5.5588
Max Act: 5.2776. Min Act: -0.1700
Data Index: 2434365 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5588. Min Range: -5.5588
Max Act: 5.2776. Min Act: -0.1700
Data Index: 100220 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5588. Min Range: -5.5588
Max Act: 5.2463. Min Act: -0.1700
Data Index: 701296 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5588. Min Range: -5.5588
Max Act: 5.2463. Min Act: -0.1700
Data Index: 4588703 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5588. Min Range: -5.5588
Max Act: 5.2151. Min Act: -0.1700
Data Index: 6874390 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5588. Min Range: -5.5588
Max Act: 5.2151. Min Act: -0.1700
Data Index: 1053582 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5588. Min Range: -5.5588
Max Act: 5.2463. Min Act: -0.1700
Data Index: 3668672 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5588. Min Range: -5.5588
Max Act: 5.2463. Min Act: -0.1700
Data Index: 6106840 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5588. Min Range: -5.5588
Max Act: 5.2151. Min Act: -0.1700
Data Index: 8247803 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5588. Min Range: -5.5588
Max Act: 5.2151. Min Act: -0.1700
Data Index: 7527505 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5588. Min Range: -5.5588
Max Act: 5.1838. Min Act: -0.1700
Data Index: 1585804 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5588. Min Range: -5.5588
Max Act: 5.1838. Min Act: -0.1700
Data Index: 5606655 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5588. Min Range: -5.5588
Max Act: 5.1526. Min Act: -0.1700
Data Index: 8324147 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #19