Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 674 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9697. Min Range: -2.9697
Max Act: 2.9697. Min Act: -0.1700
Data Index: 7699283 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9697. Min Range: -2.9697
Max Act: 2.9222. Min Act: -0.1700
Data Index: 2844259 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9697. Min Range: -2.9697
Max Act: 2.9222. Min Act: -0.1700
Data Index: 5088064 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9697. Min Range: -2.9697
Max Act: 2.8746. Min Act: -0.1700
Data Index: 3195206 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9697. Min Range: -2.9697
Max Act: 2.8746. Min Act: -0.1700
Data Index: 6265120 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9697. Min Range: -2.9697
Max Act: 2.8111. Min Act: -0.1700
Data Index: 6807979 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9697. Min Range: -2.9697
Max Act: 2.7792. Min Act: -0.1700
Data Index: 791947 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9697. Min Range: -2.9697
Max Act: 2.7792. Min Act: -0.1700
Data Index: 6780731 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9697. Min Range: -2.9697
Max Act: 2.7313. Min Act: -0.1700
Data Index: 7488026 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9697. Min Range: -2.9697
Max Act: 2.7313. Min Act: -0.1700
Data Index: 5186276 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9697. Min Range: -2.9697
Max Act: 2.7313. Min Act: -0.1700
Data Index: 191433 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9697. Min Range: -2.9697
Max Act: 2.7153. Min Act: -0.1700
Data Index: 2607025 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9697. Min Range: -2.9697
Max Act: 2.6993. Min Act: -0.1700
Data Index: 4482845 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9697. Min Range: -2.9697
Max Act: 2.7153. Min Act: -0.1700
Data Index: 4026790 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9697. Min Range: -2.9697
Max Act: 2.7153. Min Act: -0.1700
Data Index: 5315252 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9697. Min Range: -2.9697
Max Act: 2.6673. Min Act: -0.1700
Data Index: 827218 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9697. Min Range: -2.9697
Max Act: 2.6833. Min Act: -0.1700
Data Index: 857837 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9697. Min Range: -2.9697
Max Act: 2.6673. Min Act: -0.1700
Data Index: 4755280 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9697. Min Range: -2.9697
Max Act: 2.6833. Min Act: -0.1700
Data Index: 2470340 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9697. Min Range: -2.9697
Max Act: 2.6833. Min Act: -0.1700
Data Index: 5075520 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19