Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1708 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4175. Min Range: -6.4175
Max Act: 6.4175. Min Act: -0.1700
Data Index: 6241940 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4175. Min Range: -6.4175
Max Act: 6.0425. Min Act: -0.1700
Data Index: 4498130 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4175. Min Range: -6.4175
Max Act: 6.0425. Min Act: -0.1700
Data Index: 5692267 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4175. Min Range: -6.4175
Max Act: 6.0113. Min Act: -0.1700
Data Index: 6447561 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4175. Min Range: -6.4175
Max Act: 6.0113. Min Act: -0.1700
Data Index: 1344123 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4175. Min Range: -6.4175
Max Act: 5.9175. Min Act: -0.1700
Data Index: 8240443 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4175. Min Range: -6.4175
Max Act: 5.8863. Min Act: -0.1700
Data Index: 5694645 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4175. Min Range: -6.4175
Max Act: 5.8863. Min Act: -0.1700
Data Index: 1578853 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4175. Min Range: -6.4175
Max Act: 5.9488. Min Act: -0.1700
Data Index: 4918099 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4175. Min Range: -6.4175
Max Act: 5.8863. Min Act: -0.1700
Data Index: 7202907 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4175. Min Range: -6.4175
Max Act: 5.8550. Min Act: -0.1700
Data Index: 5693409 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4175. Min Range: -6.4175
Max Act: 5.9175. Min Act: -0.1700
Data Index: 3835789 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4175. Min Range: -6.4175
Max Act: 5.8550. Min Act: -0.1700
Data Index: 3365421 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4175. Min Range: -6.4175
Max Act: 5.8238. Min Act: -0.1700
Data Index: 922537 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4175. Min Range: -6.4175
Max Act: 5.8238. Min Act: -0.1700
Data Index: 3613934 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4175. Min Range: -6.4175
Max Act: 5.8238. Min Act: -0.1700
Data Index: 7037795 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4175. Min Range: -6.4175
Max Act: 5.7925. Min Act: -0.1700
Data Index: 7009639 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4175. Min Range: -6.4175
Max Act: 5.7925. Min Act: -0.1700
Data Index: 1086311 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4175. Min Range: -6.4175
Max Act: 5.8238. Min Act: -0.1700
Data Index: 5359859 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4175. Min Range: -6.4175
Max Act: 5.7925. Min Act: -0.1700
Data Index: 7672484 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #19