Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2791 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9742. Min Range: -2.9742
Max Act: 2.9742. Min Act: -0.1700
Data Index: 6702952 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9742. Min Range: -2.9742
Max Act: 2.9425. Min Act: -0.1700
Data Index: 1107051 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9742. Min Range: -2.9742
Max Act: 2.9425. Min Act: -0.1700
Data Index: 3448899 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9742. Min Range: -2.9742
Max Act: 2.9267. Min Act: -0.1700
Data Index: 1107045 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9742. Min Range: -2.9742
Max Act: 2.9267. Min Act: -0.1700
Data Index: 6064966 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9742. Min Range: -2.9742
Max Act: 2.8950. Min Act: -0.1700
Data Index: 1107047 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9742. Min Range: -2.9742
Max Act: 2.9109. Min Act: -0.1700
Data Index: 1107041 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9742. Min Range: -2.9742
Max Act: 2.9109. Min Act: -0.1700
Data Index: 1751631 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9742. Min Range: -2.9742
Max Act: 2.8950. Min Act: -0.1700
Data Index: 1107049 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9742. Min Range: -2.9742
Max Act: 2.8791. Min Act: -0.1700
Data Index: 1107052 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9742. Min Range: -2.9742
Max Act: 2.8791. Min Act: -0.1700
Data Index: 1758444 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9742. Min Range: -2.9742
Max Act: 2.8633. Min Act: -0.1700
Data Index: 5634416 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9742. Min Range: -2.9742
Max Act: 2.8791. Min Act: -0.1700
Data Index: 516171 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9742. Min Range: -2.9742
Max Act: 2.8950. Min Act: -0.1700
Data Index: 6651499 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9742. Min Range: -2.9742
Max Act: 2.8633. Min Act: -0.1700
Data Index: 1107043 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9742. Min Range: -2.9742
Max Act: 2.8633. Min Act: -0.1700
Data Index: 1052421 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9742. Min Range: -2.9742
Max Act: 2.8633. Min Act: -0.1700
Data Index: 6644540 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9742. Min Range: -2.9742
Max Act: 2.8474. Min Act: -0.1700
Data Index: 7246515 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9742. Min Range: -2.9742
Max Act: 2.8315. Min Act: -0.1700
Data Index: 7679638 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9742. Min Range: -2.9742
Max Act: 2.8474. Min Act: -0.1700
Data Index: 4393839 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19