Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2550 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1628. Min Range: -4.1628
Max Act: 4.1628. Min Act: -0.1700
Data Index: 629171 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1628. Min Range: -4.1628
Max Act: 4.1316. Min Act: -0.1700
Data Index: 6454830 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1628. Min Range: -4.1628
Max Act: 4.0691. Min Act: -0.1700
Data Index: 1729391 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1628. Min Range: -4.1628
Max Act: 4.0691. Min Act: -0.1700
Data Index: 7325373 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1628. Min Range: -4.1628
Max Act: 4.0378. Min Act: -0.1700
Data Index: 6635286 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1628. Min Range: -4.1628
Max Act: 4.0378. Min Act: -0.1700
Data Index: 8421242 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1628. Min Range: -4.1628
Max Act: 4.0378. Min Act: -0.1700
Data Index: 7854366 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1628. Min Range: -4.1628
Max Act: 4.0378. Min Act: -0.1700
Data Index: 6724391 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1628. Min Range: -4.1628
Max Act: 4.0378. Min Act: -0.1700
Data Index: 2497202 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1628. Min Range: -4.1628
Max Act: 4.0065. Min Act: -0.1700
Data Index: 4440090 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1628. Min Range: -4.1628
Max Act: 4.0065. Min Act: -0.1700
Data Index: 2558210 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1628. Min Range: -4.1628
Max Act: 4.0065. Min Act: -0.1700
Data Index: 5790286 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1628. Min Range: -4.1628
Max Act: 4.0065. Min Act: -0.1700
Data Index: 7053920 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1628. Min Range: -4.1628
Max Act: 4.0065. Min Act: -0.1700
Data Index: 5081264 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1628. Min Range: -4.1628
Max Act: 4.0065. Min Act: -0.1700
Data Index: 2373802 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1628. Min Range: -4.1628
Max Act: 4.0065. Min Act: -0.1700
Data Index: 1078608 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1628. Min Range: -4.1628
Max Act: 4.0065. Min Act: -0.1700
Data Index: 6298394 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1628. Min Range: -4.1628
Max Act: 4.0065. Min Act: -0.1700
Data Index: 4262903 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1628. Min Range: -4.1628
Max Act: 3.9753. Min Act: -0.1700
Data Index: 3627321 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1628. Min Range: -4.1628
Max Act: 3.9753. Min Act: -0.1700
Data Index: 5310012 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #19