Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4530 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0708. Min Range: -7.0708
Max Act: 7.0708. Min Act: -0.1700
Data Index: 2214208 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0708. Min Range: -7.0708
Max Act: 6.9145. Min Act: -0.1700
Data Index: 6217005 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0708. Min Range: -7.0708
Max Act: 6.5708. Min Act: -0.1700
Data Index: 2829059 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0708. Min Range: -7.0708
Max Act: 6.5708. Min Act: -0.1700
Data Index: 3684588 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0708. Min Range: -7.0708
Max Act: 6.5708. Min Act: -0.1700
Data Index: 7482549 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0708. Min Range: -7.0708
Max Act: 6.5083. Min Act: -0.1700
Data Index: 5045039 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0708. Min Range: -7.0708
Max Act: 6.4770. Min Act: -0.1700
Data Index: 8250821 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0708. Min Range: -7.0708
Max Act: 6.4458. Min Act: -0.1700
Data Index: 6681628 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0708. Min Range: -7.0708
Max Act: 6.4145. Min Act: -0.1700
Data Index: 1587580 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0708. Min Range: -7.0708
Max Act: 6.4145. Min Act: -0.1700
Data Index: 62591 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0708. Min Range: -7.0708
Max Act: 6.3833. Min Act: -0.1700
Data Index: 1957983 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0708. Min Range: -7.0708
Max Act: 6.3520. Min Act: -0.1700
Data Index: 8275147 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0708. Min Range: -7.0708
Max Act: 6.3208. Min Act: -0.1700
Data Index: 832776 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0708. Min Range: -7.0708
Max Act: 6.3208. Min Act: -0.1700
Data Index: 7629521 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0708. Min Range: -7.0708
Max Act: 6.3208. Min Act: -0.1700
Data Index: 6797313 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0708. Min Range: -7.0708
Max Act: 6.3208. Min Act: -0.1700
Data Index: 3572089 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0708. Min Range: -7.0708
Max Act: 6.2895. Min Act: -0.1700
Data Index: 3506432 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0708. Min Range: -7.0708
Max Act: 6.2583. Min Act: -0.1700
Data Index: 3695042 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0708. Min Range: -7.0708
Max Act: 6.2895. Min Act: -0.1700
Data Index: 2762199 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0708. Min Range: -7.0708
Max Act: 6.2583. Min Act: -0.1700
Data Index: 7660524 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19