Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1043 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6672. Min Range: -6.6672
Max Act: 6.6672. Min Act: -0.1700
Data Index: 2412430 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6672. Min Range: -6.6672
Max Act: 6.2609. Min Act: -0.1700
Data Index: 7069283 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6672. Min Range: -6.6672
Max Act: 6.2609. Min Act: -0.1700
Data Index: 4563160 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6672. Min Range: -6.6672
Max Act: 6.2297. Min Act: -0.1700
Data Index: 8500488 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6672. Min Range: -6.6672
Max Act: 6.1672. Min Act: -0.1700
Data Index: 7056940 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6672. Min Range: -6.6672
Max Act: 6.1359. Min Act: -0.1700
Data Index: 6174940 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6672. Min Range: -6.6672
Max Act: 6.1359. Min Act: -0.1700
Data Index: 3355452 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6672. Min Range: -6.6672
Max Act: 6.1359. Min Act: -0.1700
Data Index: 2490332 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6672. Min Range: -6.6672
Max Act: 6.1359. Min Act: -0.1700
Data Index: 1777904 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6672. Min Range: -6.6672
Max Act: 6.1047. Min Act: -0.1700
Data Index: 4968473 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6672. Min Range: -6.6672
Max Act: 6.0734. Min Act: -0.1700
Data Index: 4860927 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6672. Min Range: -6.6672
Max Act: 6.1047. Min Act: -0.1700
Data Index: 8695612 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6672. Min Range: -6.6672
Max Act: 6.0734. Min Act: -0.1700
Data Index: 4624516 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6672. Min Range: -6.6672
Max Act: 6.0422. Min Act: -0.1700
Data Index: 8515086 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6672. Min Range: -6.6672
Max Act: 6.0734. Min Act: -0.1700
Data Index: 4128564 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6672. Min Range: -6.6672
Max Act: 6.0734. Min Act: -0.1700
Data Index: 7787054 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6672. Min Range: -6.6672
Max Act: 6.0734. Min Act: -0.1700
Data Index: 7162605 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6672. Min Range: -6.6672
Max Act: 6.0109. Min Act: -0.1700
Data Index: 3110764 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6672. Min Range: -6.6672
Max Act: 6.0422. Min Act: -0.1700
Data Index: 4205760 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6672. Min Range: -6.6672
Max Act: 6.0422. Min Act: -0.1700
Data Index: 3544157 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19