Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3472 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5611. Min Range: -2.5611
Max Act: 2.5611. Min Act: -0.1700
Data Index: 5289779 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5611. Min Range: -2.5611
Max Act: 2.5288. Min Act: -0.1700
Data Index: 8677870 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5611. Min Range: -2.5611
Max Act: 2.4964. Min Act: -0.1700
Data Index: 8036722 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5611. Min Range: -2.5611
Max Act: 2.4964. Min Act: -0.1700
Data Index: 75482 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5611. Min Range: -2.5611
Max Act: 2.5126. Min Act: -0.1700
Data Index: 45806 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5611. Min Range: -2.5611
Max Act: 2.4964. Min Act: -0.1700
Data Index: 6816283 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5611. Min Range: -2.5611
Max Act: 2.4802. Min Act: -0.1700
Data Index: 4719890 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5611. Min Range: -2.5611
Max Act: 2.4640. Min Act: -0.1700
Data Index: 8557185 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5611. Min Range: -2.5611
Max Act: 2.4964. Min Act: -0.1700
Data Index: 3174830 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5611. Min Range: -2.5611
Max Act: 2.4477. Min Act: -0.1700
Data Index: 8002452 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5611. Min Range: -2.5611
Max Act: 2.4640. Min Act: -0.1700
Data Index: 5828081 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5611. Min Range: -2.5611
Max Act: 2.4640. Min Act: -0.1700
Data Index: 2012079 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5611. Min Range: -2.5611
Max Act: 2.4640. Min Act: -0.1700
Data Index: 8812465 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5611. Min Range: -2.5611
Max Act: 2.4477. Min Act: -0.1700
Data Index: 586693 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5611. Min Range: -2.5611
Max Act: 2.4152. Min Act: -0.1700
Data Index: 5024529 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5611. Min Range: -2.5611
Max Act: 2.4477. Min Act: -0.1700
Data Index: 79737 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5611. Min Range: -2.5611
Max Act: 2.4315. Min Act: -0.1700
Data Index: 3673632 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5611. Min Range: -2.5611
Max Act: 2.4477. Min Act: -0.1700
Data Index: 1062241 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5611. Min Range: -2.5611
Max Act: 2.4477. Min Act: -0.1700
Data Index: 3678515 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5611. Min Range: -2.5611
Max Act: 2.4477. Min Act: -0.1700
Data Index: 1561813 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #19