Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1992 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8681. Min Range: -3.8681
Max Act: 3.8681. Min Act: -0.1700
Data Index: 6120839 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8681. Min Range: -3.8681
Max Act: 3.7587. Min Act: -0.1700
Data Index: 3794723 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8681. Min Range: -3.8681
Max Act: 3.7118. Min Act: -0.1700
Data Index: 4866983 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8681. Min Range: -3.8681
Max Act: 3.6961. Min Act: -0.1700
Data Index: 1130987 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8681. Min Range: -3.8681
Max Act: 3.5709. Min Act: -0.1700
Data Index: 2353178 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8681. Min Range: -3.8681
Max Act: 3.5553. Min Act: -0.1700
Data Index: 4955786 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8681. Min Range: -3.8681
Max Act: 3.5709. Min Act: -0.1700
Data Index: 8053545 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8681. Min Range: -3.8681
Max Act: 3.4770. Min Act: -0.1700
Data Index: 1162839 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8681. Min Range: -3.8681
Max Act: 3.4926. Min Act: -0.1700
Data Index: 8584543 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8681. Min Range: -3.8681
Max Act: 3.4770. Min Act: -0.1700
Data Index: 3017768 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8681. Min Range: -3.8681
Max Act: 3.4613. Min Act: -0.1700
Data Index: 5189891 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8681. Min Range: -3.8681
Max Act: 3.4456. Min Act: -0.1700
Data Index: 6004093 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8681. Min Range: -3.8681
Max Act: 3.4300. Min Act: -0.1700
Data Index: 5797430 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8681. Min Range: -3.8681
Max Act: 3.4300. Min Act: -0.1700
Data Index: 6506477 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8681. Min Range: -3.8681
Max Act: 3.4143. Min Act: -0.1700
Data Index: 8119930 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8681. Min Range: -3.8681
Max Act: 3.3986. Min Act: -0.1700
Data Index: 839669 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8681. Min Range: -3.8681
Max Act: 3.3829. Min Act: -0.1700
Data Index: 4186291 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8681. Min Range: -3.8681
Max Act: 3.3672. Min Act: -0.1700
Data Index: 1218869 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8681. Min Range: -3.8681
Max Act: 3.3672. Min Act: -0.1700
Data Index: 1063539 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8681. Min Range: -3.8681
Max Act: 3.3672. Min Act: -0.1700
Data Index: 151722 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #19