Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1108 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4764. Min Range: -6.4764
Max Act: 6.4764. Min Act: -0.1700
Data Index: 1415401 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4764. Min Range: -6.4764
Max Act: 6.3826. Min Act: -0.1700
Data Index: 4314872 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4764. Min Range: -6.4764
Max Act: 6.4139. Min Act: -0.1700
Data Index: 5593498 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4764. Min Range: -6.4764
Max Act: 6.3826. Min Act: -0.1700
Data Index: 7250871 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4764. Min Range: -6.4764
Max Act: 6.3514. Min Act: -0.1700
Data Index: 4628248 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4764. Min Range: -6.4764
Max Act: 6.2576. Min Act: -0.1700
Data Index: 113966 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4764. Min Range: -6.4764
Max Act: 6.2264. Min Act: -0.1700
Data Index: 4360061 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4764. Min Range: -6.4764
Max Act: 6.1639. Min Act: -0.1700
Data Index: 813739 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4764. Min Range: -6.4764
Max Act: 6.2264. Min Act: -0.1700
Data Index: 6562694 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4764. Min Range: -6.4764
Max Act: 6.1639. Min Act: -0.1700
Data Index: 6161539 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4764. Min Range: -6.4764
Max Act: 6.1014. Min Act: -0.1700
Data Index: 813734 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4764. Min Range: -6.4764
Max Act: 6.1639. Min Act: -0.1700
Data Index: 8443516 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4764. Min Range: -6.4764
Max Act: 6.0701. Min Act: -0.1700
Data Index: 1418598 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4764. Min Range: -6.4764
Max Act: 6.0389. Min Act: -0.1700
Data Index: 1923852 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4764. Min Range: -6.4764
Max Act: 6.1014. Min Act: -0.1700
Data Index: 6458969 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4764. Min Range: -6.4764
Max Act: 6.0701. Min Act: -0.1700
Data Index: 6568327 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4764. Min Range: -6.4764
Max Act: 6.0701. Min Act: -0.1700
Data Index: 813737 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4764. Min Range: -6.4764
Max Act: 6.0389. Min Act: -0.1700
Data Index: 2765789 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4764. Min Range: -6.4764
Max Act: 6.0076. Min Act: -0.1700
Data Index: 3956921 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4764. Min Range: -6.4764
Max Act: 5.9764. Min Act: -0.1700
Data Index: 813738 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19