Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2930 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1442. Min Range: -7.1442
Max Act: 7.0817. Min Act: -0.1700
Data Index: 4255364 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1442. Min Range: -7.1442
Max Act: 7.1442. Min Act: -0.1700
Data Index: 133259 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1442. Min Range: -7.1442
Max Act: 7.0505. Min Act: -0.1700
Data Index: 3960227 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1442. Min Range: -7.1442
Max Act: 7.0192. Min Act: -0.1700
Data Index: 1640587 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1442. Min Range: -7.1442
Max Act: 6.9255. Min Act: -0.1700
Data Index: 4307952 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1442. Min Range: -7.1442
Max Act: 6.9255. Min Act: -0.1700
Data Index: 8471010 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1442. Min Range: -7.1442
Max Act: 6.8630. Min Act: -0.1700
Data Index: 5010961 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1442. Min Range: -7.1442
Max Act: 6.8630. Min Act: -0.1700
Data Index: 177631 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1442. Min Range: -7.1442
Max Act: 6.8630. Min Act: -0.1700
Data Index: 1536395 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1442. Min Range: -7.1442
Max Act: 6.8942. Min Act: -0.1700
Data Index: 2370088 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1442. Min Range: -7.1442
Max Act: 6.8317. Min Act: -0.1700
Data Index: 4147705 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1442. Min Range: -7.1442
Max Act: 6.8630. Min Act: -0.1700
Data Index: 1291143 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1442. Min Range: -7.1442
Max Act: 6.8317. Min Act: -0.1700
Data Index: 7241523 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1442. Min Range: -7.1442
Max Act: 6.8005. Min Act: -0.1700
Data Index: 1841188 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1442. Min Range: -7.1442
Max Act: 6.7692. Min Act: -0.1700
Data Index: 2317384 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1442. Min Range: -7.1442
Max Act: 6.7692. Min Act: -0.1700
Data Index: 8563623 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1442. Min Range: -7.1442
Max Act: 6.7380. Min Act: -0.1700
Data Index: 1051866 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1442. Min Range: -7.1442
Max Act: 6.7380. Min Act: -0.1700
Data Index: 2205276 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1442. Min Range: -7.1442
Max Act: 6.7380. Min Act: -0.1700
Data Index: 1902345 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1442. Min Range: -7.1442
Max Act: 6.7067. Min Act: -0.1700
Data Index: 259509 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19