Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2893 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.4824. Min Range: -8.4824
Max Act: 8.4824. Min Act: -0.1700
Data Index: 1140625 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4824. Min Range: -8.4824
Max Act: 8.1699. Min Act: -0.1700
Data Index: 4134646 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4824. Min Range: -8.4824
Max Act: 7.9824. Min Act: -0.1700
Data Index: 373451 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4824. Min Range: -8.4824
Max Act: 7.9824. Min Act: -0.1700
Data Index: 373465 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4824. Min Range: -8.4824
Max Act: 7.8886. Min Act: -0.1700
Data Index: 2287599 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4824. Min Range: -8.4824
Max Act: 7.8261. Min Act: -0.1700
Data Index: 3996570 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4824. Min Range: -8.4824
Max Act: 7.8261. Min Act: -0.1700
Data Index: 3264475 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4824. Min Range: -8.4824
Max Act: 7.8574. Min Act: -0.1700
Data Index: 5950352 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4824. Min Range: -8.4824
Max Act: 7.7636. Min Act: -0.1700
Data Index: 3552868 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4824. Min Range: -8.4824
Max Act: 7.6699. Min Act: -0.1700
Data Index: 4254868 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4824. Min Range: -8.4824
Max Act: 7.6699. Min Act: -0.1700
Data Index: 4254866 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4824. Min Range: -8.4824
Max Act: 7.6699. Min Act: -0.1700
Data Index: 6086692 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4824. Min Range: -8.4824
Max Act: 7.6386. Min Act: -0.1700
Data Index: 6207941 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4824. Min Range: -8.4824
Max Act: 7.5761. Min Act: -0.1700
Data Index: 3108576 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4824. Min Range: -8.4824
Max Act: 7.6386. Min Act: -0.1700
Data Index: 3643565 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4824. Min Range: -8.4824
Max Act: 7.6386. Min Act: -0.1700
Data Index: 6843392 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4824. Min Range: -8.4824
Max Act: 7.5761. Min Act: -0.1700
Data Index: 6843391 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4824. Min Range: -8.4824
Max Act: 7.4824. Min Act: -0.1700
Data Index: 4954586 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4824. Min Range: -8.4824
Max Act: 7.5136. Min Act: -0.1700
Data Index: 3108585 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4824. Min Range: -8.4824
Max Act: 7.4199. Min Act: -0.1700
Data Index: 6817555 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #19