Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1184 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 11.8616. Min Range: -11.8616
Max Act: 11.8616. Min Act: -0.1700
Data Index: 5112480 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.8616. Min Range: -11.8616
Max Act: 11.7366. Min Act: -0.1700
Data Index: 6007041 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.8616. Min Range: -11.8616
Max Act: 11.3616. Min Act: -0.1700
Data Index: 6328924 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.8616. Min Range: -11.8616
Max Act: 10.6116. Min Act: -0.1700
Data Index: 7207799 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.8616. Min Range: -11.8616
Max Act: 10.4866. Min Act: -0.1700
Data Index: 46685 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.8616. Min Range: -11.8616
Max Act: 10.1741. Min Act: -0.1700
Data Index: 1642296 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.8616. Min Range: -11.8616
Max Act: 10.1741. Min Act: -0.1700
Data Index: 7651188 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.8616. Min Range: -11.8616
Max Act: 10.1741. Min Act: -0.1700
Data Index: 783052 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.8616. Min Range: -11.8616
Max Act: 10.1116. Min Act: -0.1700
Data Index: 3355968 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.8616. Min Range: -11.8616
Max Act: 10.0491. Min Act: -0.1700
Data Index: 4238999 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.8616. Min Range: -11.8616
Max Act: 9.9241. Min Act: -0.1700
Data Index: 4497804 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.8616. Min Range: -11.8616
Max Act: 9.7991. Min Act: -0.1700
Data Index: 5587938 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.8616. Min Range: -11.8616
Max Act: 9.8616. Min Act: -0.1700
Data Index: 4606471 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.8616. Min Range: -11.8616
Max Act: 9.8616. Min Act: -0.1700
Data Index: 521042 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.8616. Min Range: -11.8616
Max Act: 9.8616. Min Act: -0.1700
Data Index: 2042973 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.8616. Min Range: -11.8616
Max Act: 9.5491. Min Act: -0.1700
Data Index: 5853726 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.8616. Min Range: -11.8616
Max Act: 9.6741. Min Act: -0.1700
Data Index: 1214696 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.8616. Min Range: -11.8616
Max Act: 9.5491. Min Act: -0.1700
Data Index: 8079191 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.8616. Min Range: -11.8616
Max Act: 9.4241. Min Act: -0.1700
Data Index: 576562 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.8616. Min Range: -11.8616
Max Act: 9.7366. Min Act: -0.1700
Data Index: 2971169 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19