Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2672 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5898. Min Range: -2.5898
Max Act: 2.5898. Min Act: -0.1700
Data Index: 8391391 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5898. Min Range: -2.5898
Max Act: 2.5575. Min Act: -0.1700
Data Index: 3526212 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5898. Min Range: -2.5898
Max Act: 2.5414. Min Act: -0.1700
Data Index: 8356545 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5898. Min Range: -2.5898
Max Act: 2.5252. Min Act: -0.1700
Data Index: 7884571 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5898. Min Range: -2.5898
Max Act: 2.4766. Min Act: -0.1700
Data Index: 4744317 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5898. Min Range: -2.5898
Max Act: 2.4766. Min Act: -0.1700
Data Index: 8121670 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5898. Min Range: -2.5898
Max Act: 2.4604. Min Act: -0.1700
Data Index: 2564674 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5898. Min Range: -2.5898
Max Act: 2.4604. Min Act: -0.1700
Data Index: 2914880 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5898. Min Range: -2.5898
Max Act: 2.4279. Min Act: -0.1700
Data Index: 7775999 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5898. Min Range: -2.5898
Max Act: 2.4604. Min Act: -0.1700
Data Index: 3105838 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5898. Min Range: -2.5898
Max Act: 2.4279. Min Act: -0.1700
Data Index: 2617555 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5898. Min Range: -2.5898
Max Act: 2.4116. Min Act: -0.1700
Data Index: 5119243 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5898. Min Range: -2.5898
Max Act: 2.4279. Min Act: -0.1700
Data Index: 8032791 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5898. Min Range: -2.5898
Max Act: 2.4279. Min Act: -0.1700
Data Index: 5343580 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5898. Min Range: -2.5898
Max Act: 2.4441. Min Act: -0.1700
Data Index: 3592883 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5898. Min Range: -2.5898
Max Act: 2.3953. Min Act: -0.1700
Data Index: 4369675 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5898. Min Range: -2.5898
Max Act: 2.3953. Min Act: -0.1700
Data Index: 6904068 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5898. Min Range: -2.5898
Max Act: 2.3789. Min Act: -0.1700
Data Index: 2362854 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5898. Min Range: -2.5898
Max Act: 2.3626. Min Act: -0.1700
Data Index: 8109132 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5898. Min Range: -2.5898
Max Act: 2.3953. Min Act: -0.1700
Data Index: 3819825 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19