Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3258 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7889. Min Range: -5.7889
Max Act: 5.7889. Min Act: -0.1700
Data Index: 1606642 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7889. Min Range: -5.7889
Max Act: 5.7264. Min Act: -0.1700
Data Index: 5444018 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7889. Min Range: -5.7889
Max Act: 5.7264. Min Act: -0.1700
Data Index: 1606655 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7889. Min Range: -5.7889
Max Act: 5.6327. Min Act: -0.1700
Data Index: 4865329 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7889. Min Range: -5.7889
Max Act: 5.5702. Min Act: -0.1700
Data Index: 1028848 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7889. Min Range: -5.7889
Max Act: 5.4764. Min Act: -0.1700
Data Index: 2746211 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7889. Min Range: -5.7889
Max Act: 5.5077. Min Act: -0.1700
Data Index: 6690288 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7889. Min Range: -5.7889
Max Act: 5.5077. Min Act: -0.1700
Data Index: 7151051 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7889. Min Range: -5.7889
Max Act: 5.4764. Min Act: -0.1700
Data Index: 215939 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7889. Min Range: -5.7889
Max Act: 5.3827. Min Act: -0.1700
Data Index: 3780498 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7889. Min Range: -5.7889
Max Act: 5.3827. Min Act: -0.1700
Data Index: 5763345 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7889. Min Range: -5.7889
Max Act: 5.3827. Min Act: -0.1700
Data Index: 5735325 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7889. Min Range: -5.7889
Max Act: 5.3827. Min Act: -0.1700
Data Index: 113852 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7889. Min Range: -5.7889
Max Act: 5.4139. Min Act: -0.1700
Data Index: 2454275 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7889. Min Range: -5.7889
Max Act: 5.4139. Min Act: -0.1700
Data Index: 215938 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7889. Min Range: -5.7889
Max Act: 5.3202. Min Act: -0.1700
Data Index: 3359155 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7889. Min Range: -5.7889
Max Act: 5.3202. Min Act: -0.1700
Data Index: 488638 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7889. Min Range: -5.7889
Max Act: 5.3202. Min Act: -0.1700
Data Index: 3780497 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7889. Min Range: -5.7889
Max Act: 5.3202. Min Act: -0.1700
Data Index: 579552 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7889. Min Range: -5.7889
Max Act: 5.3202. Min Act: -0.1700
Data Index: 4822129 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19