Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1980 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7906. Min Range: -2.7906
Max Act: 2.7906. Min Act: -0.1700
Data Index: 8308403 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7906. Min Range: -2.7906
Max Act: 2.7268. Min Act: -0.1700
Data Index: 302649 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7906. Min Range: -2.7906
Max Act: 2.7427. Min Act: -0.1700
Data Index: 3371825 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7906. Min Range: -2.7906
Max Act: 2.6788. Min Act: -0.1700
Data Index: 4806389 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7906. Min Range: -2.7906
Max Act: 2.6306. Min Act: -0.1700
Data Index: 830230 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7906. Min Range: -2.7906
Max Act: 2.6146. Min Act: -0.1700
Data Index: 1851033 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7906. Min Range: -2.7906
Max Act: 2.5824. Min Act: -0.1700
Data Index: 3423302 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7906. Min Range: -2.7906
Max Act: 2.5985. Min Act: -0.1700
Data Index: 4805211 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7906. Min Range: -2.7906
Max Act: 2.5501. Min Act: -0.1700
Data Index: 3074273 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7906. Min Range: -2.7906
Max Act: 2.5662. Min Act: -0.1700
Data Index: 7119806 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7906. Min Range: -2.7906
Max Act: 2.5340. Min Act: -0.1700
Data Index: 2017748 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7906. Min Range: -2.7906
Max Act: 2.5501. Min Act: -0.1700
Data Index: 2582407 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7906. Min Range: -2.7906
Max Act: 2.5340. Min Act: -0.1700
Data Index: 5182576 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7906. Min Range: -2.7906
Max Act: 2.5340. Min Act: -0.1700
Data Index: 3235609 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7906. Min Range: -2.7906
Max Act: 2.5340. Min Act: -0.1700
Data Index: 3659953 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7906. Min Range: -2.7906
Max Act: 2.5178. Min Act: -0.1700
Data Index: 831667 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7906. Min Range: -2.7906
Max Act: 2.5662. Min Act: -0.1700
Data Index: 5832393 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7906. Min Range: -2.7906
Max Act: 2.5178. Min Act: -0.1700
Data Index: 5818306 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7906. Min Range: -2.7906
Max Act: 2.5340. Min Act: -0.1700
Data Index: 536315 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7906. Min Range: -2.7906
Max Act: 2.5178. Min Act: -0.1700
Data Index: 6142930 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19