Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 18 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8901. Min Range: -5.8901
Max Act: 5.8901. Min Act: -0.1700
Data Index: 7054560 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8901. Min Range: -5.8901
Max Act: 5.7339. Min Act: -0.1700
Data Index: 7007880 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8901. Min Range: -5.8901
Max Act: 5.7339. Min Act: -0.1700
Data Index: 8756100 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8901. Min Range: -5.8901
Max Act: 5.6714. Min Act: -0.1700
Data Index: 8685019 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8901. Min Range: -5.8901
Max Act: 5.6714. Min Act: -0.1700
Data Index: 537128 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8901. Min Range: -5.8901
Max Act: 5.5151. Min Act: -0.1700
Data Index: 3333438 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8901. Min Range: -5.8901
Max Act: 5.4839. Min Act: -0.1700
Data Index: 6468148 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8901. Min Range: -5.8901
Max Act: 5.5151. Min Act: -0.1700
Data Index: 3869202 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8901. Min Range: -5.8901
Max Act: 5.4526. Min Act: -0.1700
Data Index: 170296 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8901. Min Range: -5.8901
Max Act: 5.3901. Min Act: -0.1700
Data Index: 4653898 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8901. Min Range: -5.8901
Max Act: 5.3901. Min Act: -0.1700
Data Index: 3677712 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8901. Min Range: -5.8901
Max Act: 5.3901. Min Act: -0.1700
Data Index: 3662670 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8901. Min Range: -5.8901
Max Act: 5.3276. Min Act: -0.1700
Data Index: 890076 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8901. Min Range: -5.8901
Max Act: 5.2964. Min Act: -0.1700
Data Index: 1337701 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8901. Min Range: -5.8901
Max Act: 5.2964. Min Act: -0.1700
Data Index: 8078508 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8901. Min Range: -5.8901
Max Act: 5.2651. Min Act: -0.1700
Data Index: 8315570 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8901. Min Range: -5.8901
Max Act: 5.2339. Min Act: -0.1700
Data Index: 5216623 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8901. Min Range: -5.8901
Max Act: 5.1714. Min Act: -0.1700
Data Index: 2028130 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8901. Min Range: -5.8901
Max Act: 5.1714. Min Act: -0.1700
Data Index: 6243152 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8901. Min Range: -5.8901
Max Act: 5.1714. Min Act: -0.1700
Data Index: 7200226 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #19