Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4048 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.5014. Min Act: -0.1700
Data Index: 8595569 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.2827. Min Act: -0.1700
Data Index: 3126431 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.2827. Min Act: -0.1700
Data Index: 804530 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.1889. Min Act: -0.1700
Data Index: 2851914 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.1577. Min Act: -0.1700
Data Index: 1597652 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.1889. Min Act: -0.1700
Data Index: 2443247 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.1264. Min Act: -0.1700
Data Index: 6632792 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.1264. Min Act: -0.1700
Data Index: 4247131 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.1264. Min Act: -0.1700
Data Index: 8231470 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.0952. Min Act: -0.1700
Data Index: 6230751 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.0952. Min Act: -0.1700
Data Index: 1083204 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.0952. Min Act: -0.1700
Data Index: 3967544 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.0327. Min Act: -0.1700
Data Index: 1210872 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.0639. Min Act: -0.1700
Data Index: 4440159 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.0639. Min Act: -0.1700
Data Index: 660489 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.0639. Min Act: -0.1700
Data Index: 4013784 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.0327. Min Act: -0.1700
Data Index: 4972941 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.0639. Min Act: -0.1700
Data Index: 3438003 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.0014. Min Act: -0.1700
Data Index: 2682635 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.0014. Min Act: -0.1700
Data Index: 467666 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #19