Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3146 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0454. Min Range: -6.0454
Max Act: 6.0454. Min Act: -0.1700
Data Index: 3747878 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0454. Min Range: -6.0454
Max Act: 5.9829. Min Act: -0.1700
Data Index: 5160531 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0454. Min Range: -6.0454
Max Act: 6.0141. Min Act: -0.1700
Data Index: 8475737 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0454. Min Range: -6.0454
Max Act: 5.9204. Min Act: -0.1700
Data Index: 5149070 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0454. Min Range: -6.0454
Max Act: 5.9204. Min Act: -0.1700
Data Index: 2361778 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0454. Min Range: -6.0454
Max Act: 5.8891. Min Act: -0.1700
Data Index: 804654 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0454. Min Range: -6.0454
Max Act: 5.8579. Min Act: -0.1700
Data Index: 8603405 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0454. Min Range: -6.0454
Max Act: 5.8579. Min Act: -0.1700
Data Index: 3280409 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0454. Min Range: -6.0454
Max Act: 5.7641. Min Act: -0.1700
Data Index: 6737202 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0454. Min Range: -6.0454
Max Act: 5.8266. Min Act: -0.1700
Data Index: 3981952 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0454. Min Range: -6.0454
Max Act: 5.7641. Min Act: -0.1700
Data Index: 6007013 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0454. Min Range: -6.0454
Max Act: 5.7641. Min Act: -0.1700
Data Index: 1185764 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0454. Min Range: -6.0454
Max Act: 5.7954. Min Act: -0.1700
Data Index: 3408085 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0454. Min Range: -6.0454
Max Act: 5.7954. Min Act: -0.1700
Data Index: 4201153 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0454. Min Range: -6.0454
Max Act: 5.7641. Min Act: -0.1700
Data Index: 7878341 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0454. Min Range: -6.0454
Max Act: 5.7641. Min Act: -0.1700
Data Index: 5928809 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0454. Min Range: -6.0454
Max Act: 5.7954. Min Act: -0.1700
Data Index: 5390443 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0454. Min Range: -6.0454
Max Act: 5.7954. Min Act: -0.1700
Data Index: 2643394 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0454. Min Range: -6.0454
Max Act: 5.7329. Min Act: -0.1700
Data Index: 7238225 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0454. Min Range: -6.0454
Max Act: 5.7329. Min Act: -0.1700
Data Index: 6410153 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19