Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2224 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2044. Min Range: -6.2044
Max Act: 6.2044. Min Act: -0.1700
Data Index: 5887284 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2044. Min Range: -6.2044
Max Act: 6.0481. Min Act: -0.1700
Data Index: 6341978 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2044. Min Range: -6.2044
Max Act: 6.0481. Min Act: -0.1700
Data Index: 4213634 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2044. Min Range: -6.2044
Max Act: 5.8606. Min Act: -0.1700
Data Index: 5480649 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2044. Min Range: -6.2044
Max Act: 5.8919. Min Act: -0.1700
Data Index: 3796773 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2044. Min Range: -6.2044
Max Act: 5.8294. Min Act: -0.1700
Data Index: 5945126 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2044. Min Range: -6.2044
Max Act: 5.7981. Min Act: -0.1700
Data Index: 4899058 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2044. Min Range: -6.2044
Max Act: 5.7669. Min Act: -0.1700
Data Index: 8246664 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2044. Min Range: -6.2044
Max Act: 5.7669. Min Act: -0.1700
Data Index: 289270 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2044. Min Range: -6.2044
Max Act: 5.7044. Min Act: -0.1700
Data Index: 4502319 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2044. Min Range: -6.2044
Max Act: 5.6106. Min Act: -0.1700
Data Index: 6234110 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2044. Min Range: -6.2044
Max Act: 5.6419. Min Act: -0.1700
Data Index: 6307889 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2044. Min Range: -6.2044
Max Act: 5.6731. Min Act: -0.1700
Data Index: 2662374 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2044. Min Range: -6.2044
Max Act: 5.6731. Min Act: -0.1700
Data Index: 4109164 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2044. Min Range: -6.2044
Max Act: 5.6106. Min Act: -0.1700
Data Index: 1426539 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2044. Min Range: -6.2044
Max Act: 5.6106. Min Act: -0.1700
Data Index: 8537849 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2044. Min Range: -6.2044
Max Act: 5.6731. Min Act: -0.1700
Data Index: 1811020 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2044. Min Range: -6.2044
Max Act: 5.6106. Min Act: -0.1700
Data Index: 6141075 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2044. Min Range: -6.2044
Max Act: 5.6106. Min Act: -0.1700
Data Index: 370791 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2044. Min Range: -6.2044
Max Act: 5.5794. Min Act: -0.1700
Data Index: 4153298 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19