Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 53 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0384. Min Range: -4.0384
Max Act: 4.0072. Min Act: -0.1700
Data Index: 8792093 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0384. Min Range: -4.0384
Max Act: 4.0072. Min Act: -0.1700
Data Index: 2580982 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0384. Min Range: -4.0384
Max Act: 4.0384. Min Act: -0.1700
Data Index: 8319311 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0384. Min Range: -4.0384
Max Act: 4.0384. Min Act: -0.1700
Data Index: 6788409 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0384. Min Range: -4.0384
Max Act: 4.0384. Min Act: -0.1700
Data Index: 241485 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0384. Min Range: -4.0384
Max Act: 4.0384. Min Act: -0.1700
Data Index: 4152266 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0384. Min Range: -4.0384
Max Act: 3.9759. Min Act: -0.1700
Data Index: 7728927 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0384. Min Range: -4.0384
Max Act: 4.0072. Min Act: -0.1700
Data Index: 5539697 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0384. Min Range: -4.0384
Max Act: 3.9759. Min Act: -0.1700
Data Index: 7793548 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0384. Min Range: -4.0384
Max Act: 4.0072. Min Act: -0.1700
Data Index: 7173224 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0384. Min Range: -4.0384
Max Act: 3.9759. Min Act: -0.1700
Data Index: 5425203 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0384. Min Range: -4.0384
Max Act: 3.9447. Min Act: -0.1700
Data Index: 8422704 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0384. Min Range: -4.0384
Max Act: 3.8821. Min Act: -0.1700
Data Index: 3803584 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0384. Min Range: -4.0384
Max Act: 3.9134. Min Act: -0.1700
Data Index: 2851567 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0384. Min Range: -4.0384
Max Act: 3.8821. Min Act: -0.1700
Data Index: 6861560 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0384. Min Range: -4.0384
Max Act: 3.9134. Min Act: -0.1700
Data Index: 2401727 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0384. Min Range: -4.0384
Max Act: 3.8821. Min Act: -0.1700
Data Index: 5014930 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0384. Min Range: -4.0384
Max Act: 3.8509. Min Act: -0.1700
Data Index: 5443866 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0384. Min Range: -4.0384
Max Act: 3.9134. Min Act: -0.1700
Data Index: 822696 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0384. Min Range: -4.0384
Max Act: 3.8821. Min Act: -0.1700
Data Index: 6313522 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19