Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2674 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2795. Min Range: -6.2795
Max Act: 6.2795. Min Act: -0.1700
Data Index: 6826003 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2795. Min Range: -6.2795
Max Act: 6.0607. Min Act: -0.1700
Data Index: 7181842 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2795. Min Range: -6.2795
Max Act: 5.9670. Min Act: -0.1700
Data Index: 2971828 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2795. Min Range: -6.2795
Max Act: 5.9357. Min Act: -0.1700
Data Index: 7062777 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2795. Min Range: -6.2795
Max Act: 5.8732. Min Act: -0.1700
Data Index: 4440399 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2795. Min Range: -6.2795
Max Act: 5.8420. Min Act: -0.1700
Data Index: 8490554 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2795. Min Range: -6.2795
Max Act: 5.8107. Min Act: -0.1700
Data Index: 6345410 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2795. Min Range: -6.2795
Max Act: 5.8107. Min Act: -0.1700
Data Index: 2399934 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2795. Min Range: -6.2795
Max Act: 5.7795. Min Act: -0.1700
Data Index: 1771924 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2795. Min Range: -6.2795
Max Act: 5.8107. Min Act: -0.1700
Data Index: 7985057 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2795. Min Range: -6.2795
Max Act: 5.7482. Min Act: -0.1700
Data Index: 5537891 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2795. Min Range: -6.2795
Max Act: 5.7482. Min Act: -0.1700
Data Index: 7729724 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2795. Min Range: -6.2795
Max Act: 5.7482. Min Act: -0.1700
Data Index: 7349330 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2795. Min Range: -6.2795
Max Act: 5.7170. Min Act: -0.1700
Data Index: 3231838 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2795. Min Range: -6.2795
Max Act: 5.7170. Min Act: -0.1700
Data Index: 5028113 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2795. Min Range: -6.2795
Max Act: 5.6857. Min Act: -0.1700
Data Index: 5155328 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2795. Min Range: -6.2795
Max Act: 5.6545. Min Act: -0.1700
Data Index: 1576915 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2795. Min Range: -6.2795
Max Act: 5.6857. Min Act: -0.1700
Data Index: 5952597 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2795. Min Range: -6.2795
Max Act: 5.7170. Min Act: -0.1700
Data Index: 5504501 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2795. Min Range: -6.2795
Max Act: 5.7170. Min Act: -0.1700
Data Index: 6151791 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19