Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2475 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9332. Min Range: -5.9332
Max Act: 5.9332. Min Act: -0.1700
Data Index: 4043924 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9332. Min Range: -5.9332
Max Act: 5.7144. Min Act: -0.1700
Data Index: 5643857 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9332. Min Range: -5.9332
Max Act: 5.5894. Min Act: -0.1700
Data Index: 4910166 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9332. Min Range: -5.9332
Max Act: 5.4957. Min Act: -0.1700
Data Index: 2966317 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9332. Min Range: -5.9332
Max Act: 5.4644. Min Act: -0.1700
Data Index: 4191238 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9332. Min Range: -5.9332
Max Act: 5.4332. Min Act: -0.1700
Data Index: 3343931 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9332. Min Range: -5.9332
Max Act: 5.4332. Min Act: -0.1700
Data Index: 771697 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9332. Min Range: -5.9332
Max Act: 5.4332. Min Act: -0.1700
Data Index: 6812334 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9332. Min Range: -5.9332
Max Act: 5.4332. Min Act: -0.1700
Data Index: 708655 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9332. Min Range: -5.9332
Max Act: 5.4332. Min Act: -0.1700
Data Index: 5658648 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9332. Min Range: -5.9332
Max Act: 5.4019. Min Act: -0.1700
Data Index: 8245325 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9332. Min Range: -5.9332
Max Act: 5.4019. Min Act: -0.1700
Data Index: 907914 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9332. Min Range: -5.9332
Max Act: 5.3707. Min Act: -0.1700
Data Index: 2928061 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9332. Min Range: -5.9332
Max Act: 5.4019. Min Act: -0.1700
Data Index: 2987158 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9332. Min Range: -5.9332
Max Act: 5.4332. Min Act: -0.1700
Data Index: 5344652 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9332. Min Range: -5.9332
Max Act: 5.4019. Min Act: -0.1700
Data Index: 3427503 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9332. Min Range: -5.9332
Max Act: 5.3707. Min Act: -0.1700
Data Index: 5981779 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9332. Min Range: -5.9332
Max Act: 5.3707. Min Act: -0.1700
Data Index: 2689408 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9332. Min Range: -5.9332
Max Act: 5.3707. Min Act: -0.1700
Data Index: 4175242 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9332. Min Range: -5.9332
Max Act: 5.3707. Min Act: -0.1700
Data Index: 3780500 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19