Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2284 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0879. Min Range: -7.0879
Max Act: 7.0879. Min Act: -0.1700
Data Index: 3566615 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0879. Min Range: -7.0879
Max Act: 6.8379. Min Act: -0.1700
Data Index: 1055410 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0879. Min Range: -7.0879
Max Act: 6.3692. Min Act: -0.1700
Data Index: 3490061 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0879. Min Range: -7.0879
Max Act: 6.3379. Min Act: -0.1700
Data Index: 793820 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0879. Min Range: -7.0879
Max Act: 6.3692. Min Act: -0.1700
Data Index: 1367117 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0879. Min Range: -7.0879
Max Act: 6.3379. Min Act: -0.1700
Data Index: 4655305 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0879. Min Range: -7.0879
Max Act: 6.2754. Min Act: -0.1700
Data Index: 1728951 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0879. Min Range: -7.0879
Max Act: 6.2754. Min Act: -0.1700
Data Index: 5822170 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0879. Min Range: -7.0879
Max Act: 6.2442. Min Act: -0.1700
Data Index: 5454437 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0879. Min Range: -7.0879
Max Act: 6.2442. Min Act: -0.1700
Data Index: 2240895 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0879. Min Range: -7.0879
Max Act: 6.2442. Min Act: -0.1700
Data Index: 4249659 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0879. Min Range: -7.0879
Max Act: 6.2442. Min Act: -0.1700
Data Index: 6341212 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0879. Min Range: -7.0879
Max Act: 6.2129. Min Act: -0.1700
Data Index: 1166893 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0879. Min Range: -7.0879
Max Act: 6.2129. Min Act: -0.1700
Data Index: 5834822 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0879. Min Range: -7.0879
Max Act: 6.1817. Min Act: -0.1700
Data Index: 2359148 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0879. Min Range: -7.0879
Max Act: 6.1504. Min Act: -0.1700
Data Index: 8063706 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0879. Min Range: -7.0879
Max Act: 6.0567. Min Act: -0.1700
Data Index: 1603952 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0879. Min Range: -7.0879
Max Act: 6.0879. Min Act: -0.1700
Data Index: 4898316 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0879. Min Range: -7.0879
Max Act: 6.0567. Min Act: -0.1700
Data Index: 1568937 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0879. Min Range: -7.0879
Max Act: 6.0879. Min Act: -0.1700
Data Index: 5318702 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #19