Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3882 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6639. Min Range: -3.6639
Max Act: 3.6639. Min Act: -0.1700
Data Index: 5644155 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6639. Min Range: -3.6639
Max Act: 3.6326. Min Act: -0.1700
Data Index: 430545 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6639. Min Range: -3.6639
Max Act: 3.6326. Min Act: -0.1700
Data Index: 2952488 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6639. Min Range: -3.6639
Max Act: 3.6013. Min Act: -0.1700
Data Index: 2823246 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6639. Min Range: -3.6639
Max Act: 3.5700. Min Act: -0.1700
Data Index: 6665547 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6639. Min Range: -3.6639
Max Act: 3.5700. Min Act: -0.1700
Data Index: 1328095 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6639. Min Range: -3.6639
Max Act: 3.5700. Min Act: -0.1700
Data Index: 3463269 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6639. Min Range: -3.6639
Max Act: 3.5387. Min Act: -0.1700
Data Index: 58562 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6639. Min Range: -3.6639
Max Act: 3.5544. Min Act: -0.1700
Data Index: 4208120 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6639. Min Range: -3.6639
Max Act: 3.5544. Min Act: -0.1700
Data Index: 7775690 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6639. Min Range: -3.6639
Max Act: 3.5231. Min Act: -0.1700
Data Index: 2035699 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6639. Min Range: -3.6639
Max Act: 3.5074. Min Act: -0.1700
Data Index: 2843959 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6639. Min Range: -3.6639
Max Act: 3.5074. Min Act: -0.1700
Data Index: 4196034 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6639. Min Range: -3.6639
Max Act: 3.4917. Min Act: -0.1700
Data Index: 7204214 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6639. Min Range: -3.6639
Max Act: 3.4917. Min Act: -0.1700
Data Index: 450694 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6639. Min Range: -3.6639
Max Act: 3.5231. Min Act: -0.1700
Data Index: 4544604 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6639. Min Range: -3.6639
Max Act: 3.4761. Min Act: -0.1700
Data Index: 7873823 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6639. Min Range: -3.6639
Max Act: 3.4761. Min Act: -0.1700
Data Index: 6239340 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6639. Min Range: -3.6639
Max Act: 3.4604. Min Act: -0.1700
Data Index: 5823875 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6639. Min Range: -3.6639
Max Act: 3.4761. Min Act: -0.1700
Data Index: 5964560 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #19