Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 835 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0521. Min Range: -3.0521
Max Act: 3.0521. Min Act: -0.1700
Data Index: 3960213 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0521. Min Range: -3.0521
Max Act: 2.9731. Min Act: -0.1700
Data Index: 3837354 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0521. Min Range: -3.0521
Max Act: 2.9573. Min Act: -0.1700
Data Index: 983008 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0521. Min Range: -3.0521
Max Act: 2.9573. Min Act: -0.1700
Data Index: 988666 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0521. Min Range: -3.0521
Max Act: 2.9573. Min Act: -0.1700
Data Index: 6885281 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0521. Min Range: -3.0521
Max Act: 2.9731. Min Act: -0.1700
Data Index: 7409025 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0521. Min Range: -3.0521
Max Act: 2.9257. Min Act: -0.1700
Data Index: 2911129 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0521. Min Range: -3.0521
Max Act: 2.9257. Min Act: -0.1700
Data Index: 2383010 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0521. Min Range: -3.0521
Max Act: 2.9098. Min Act: -0.1700
Data Index: 1063670 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0521. Min Range: -3.0521
Max Act: 2.9098. Min Act: -0.1700
Data Index: 5413289 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0521. Min Range: -3.0521
Max Act: 2.9257. Min Act: -0.1700
Data Index: 4613585 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0521. Min Range: -3.0521
Max Act: 2.8939. Min Act: -0.1700
Data Index: 8455040 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0521. Min Range: -3.0521
Max Act: 2.9257. Min Act: -0.1700
Data Index: 1097323 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0521. Min Range: -3.0521
Max Act: 2.8939. Min Act: -0.1700
Data Index: 3451090 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0521. Min Range: -3.0521
Max Act: 2.8622. Min Act: -0.1700
Data Index: 892551 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0521. Min Range: -3.0521
Max Act: 2.8939. Min Act: -0.1700
Data Index: 754498 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0521. Min Range: -3.0521
Max Act: 2.8781. Min Act: -0.1700
Data Index: 7633785 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0521. Min Range: -3.0521
Max Act: 2.8939. Min Act: -0.1700
Data Index: 4797930 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0521. Min Range: -3.0521
Max Act: 2.8622. Min Act: -0.1700
Data Index: 3133084 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0521. Min Range: -3.0521
Max Act: 2.8781. Min Act: -0.1700
Data Index: 4610387 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19