Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3690 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9025. Min Range: -3.9025
Max Act: 3.9025. Min Act: -0.1700
Data Index: 781800 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9025. Min Range: -3.9025
Max Act: 3.9025. Min Act: -0.1700
Data Index: 6105927 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9025. Min Range: -3.9025
Max Act: 3.9025. Min Act: -0.1700
Data Index: 3140808 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9025. Min Range: -3.9025
Max Act: 3.8712. Min Act: -0.1700
Data Index: 4097016 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9025. Min Range: -3.9025
Max Act: 3.8712. Min Act: -0.1700
Data Index: 4989805 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9025. Min Range: -3.9025
Max Act: 3.8556. Min Act: -0.1700
Data Index: 5918253 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9025. Min Range: -3.9025
Max Act: 3.8712. Min Act: -0.1700
Data Index: 6635456 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9025. Min Range: -3.9025
Max Act: 3.8556. Min Act: -0.1700
Data Index: 3894266 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9025. Min Range: -3.9025
Max Act: 3.8556. Min Act: -0.1700
Data Index: 2233264 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9025. Min Range: -3.9025
Max Act: 3.8399. Min Act: -0.1700
Data Index: 3276862 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9025. Min Range: -3.9025
Max Act: 3.8399. Min Act: -0.1700
Data Index: 3373911 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9025. Min Range: -3.9025
Max Act: 3.8086. Min Act: -0.1700
Data Index: 3911682 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9025. Min Range: -3.9025
Max Act: 3.8086. Min Act: -0.1700
Data Index: 3531837 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9025. Min Range: -3.9025
Max Act: 3.7774. Min Act: -0.1700
Data Index: 8823840 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9025. Min Range: -3.9025
Max Act: 3.7930. Min Act: -0.1700
Data Index: 1902516 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9025. Min Range: -3.9025
Max Act: 3.7461. Min Act: -0.1700
Data Index: 601522 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9025. Min Range: -3.9025
Max Act: 3.7774. Min Act: -0.1700
Data Index: 6998297 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9025. Min Range: -3.9025
Max Act: 3.7305. Min Act: -0.1700
Data Index: 6264493 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9025. Min Range: -3.9025
Max Act: 3.7461. Min Act: -0.1700
Data Index: 5098463 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9025. Min Range: -3.9025
Max Act: 3.7305. Min Act: -0.1700
Data Index: 6813471 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19