Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2576 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9655. Min Range: -2.9655
Max Act: 2.9655. Min Act: -0.1700
Data Index: 4513892 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9655. Min Range: -2.9655
Max Act: 2.8704. Min Act: -0.1700
Data Index: 4143406 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9655. Min Range: -2.9655
Max Act: 2.8386. Min Act: -0.1700
Data Index: 3693407 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9655. Min Range: -2.9655
Max Act: 2.7909. Min Act: -0.1700
Data Index: 2589175 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9655. Min Range: -2.9655
Max Act: 2.7909. Min Act: -0.1700
Data Index: 5229801 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9655. Min Range: -2.9655
Max Act: 2.8068. Min Act: -0.1700
Data Index: 6432335 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9655. Min Range: -2.9655
Max Act: 2.8068. Min Act: -0.1700
Data Index: 5028698 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9655. Min Range: -2.9655
Max Act: 2.7909. Min Act: -0.1700
Data Index: 3138650 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9655. Min Range: -2.9655
Max Act: 2.7590. Min Act: -0.1700
Data Index: 3946708 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9655. Min Range: -2.9655
Max Act: 2.7749. Min Act: -0.1700
Data Index: 4229685 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9655. Min Range: -2.9655
Max Act: 2.7749. Min Act: -0.1700
Data Index: 368127 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9655. Min Range: -2.9655
Max Act: 2.7590. Min Act: -0.1700
Data Index: 5366586 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9655. Min Range: -2.9655
Max Act: 2.7590. Min Act: -0.1700
Data Index: 6108465 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9655. Min Range: -2.9655
Max Act: 2.7430. Min Act: -0.1700
Data Index: 4874080 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9655. Min Range: -2.9655
Max Act: 2.7430. Min Act: -0.1700
Data Index: 5028697 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9655. Min Range: -2.9655
Max Act: 2.7270. Min Act: -0.1700
Data Index: 2307674 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9655. Min Range: -2.9655
Max Act: 2.7110. Min Act: -0.1700
Data Index: 904206 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9655. Min Range: -2.9655
Max Act: 2.7110. Min Act: -0.1700
Data Index: 7226167 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9655. Min Range: -2.9655
Max Act: 2.7110. Min Act: -0.1700
Data Index: 5174344 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9655. Min Range: -2.9655
Max Act: 2.7110. Min Act: -0.1700
Data Index: 70536 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #19