Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4597 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6692. Min Range: -4.6692
Max Act: 4.6692. Min Act: -0.1700
Data Index: 1866870 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6692. Min Range: -4.6692
Max Act: 4.6692. Min Act: -0.1700
Data Index: 4926037 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6692. Min Range: -4.6692
Max Act: 4.6067. Min Act: -0.1700
Data Index: 6994646 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6692. Min Range: -4.6692
Max Act: 4.5442. Min Act: -0.1700
Data Index: 1938893 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6692. Min Range: -4.6692
Max Act: 4.5129. Min Act: -0.1700
Data Index: 280888 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6692. Min Range: -4.6692
Max Act: 4.5129. Min Act: -0.1700
Data Index: 8281571 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6692. Min Range: -4.6692
Max Act: 4.4817. Min Act: -0.1700
Data Index: 782529 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6692. Min Range: -4.6692
Max Act: 4.4192. Min Act: -0.1700
Data Index: 6310487 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6692. Min Range: -4.6692
Max Act: 4.4504. Min Act: -0.1700
Data Index: 6019611 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6692. Min Range: -4.6692
Max Act: 4.4504. Min Act: -0.1700
Data Index: 5272418 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6692. Min Range: -4.6692
Max Act: 4.3879. Min Act: -0.1700
Data Index: 500412 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6692. Min Range: -4.6692
Max Act: 4.3879. Min Act: -0.1700
Data Index: 4745287 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6692. Min Range: -4.6692
Max Act: 4.3879. Min Act: -0.1700
Data Index: 3993436 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6692. Min Range: -4.6692
Max Act: 4.3879. Min Act: -0.1700
Data Index: 5903178 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6692. Min Range: -4.6692
Max Act: 4.3879. Min Act: -0.1700
Data Index: 5209818 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6692. Min Range: -4.6692
Max Act: 4.3879. Min Act: -0.1700
Data Index: 6450905 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6692. Min Range: -4.6692
Max Act: 4.3567. Min Act: -0.1700
Data Index: 8139313 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6692. Min Range: -4.6692
Max Act: 4.3567. Min Act: -0.1700
Data Index: 5723472 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6692. Min Range: -4.6692
Max Act: 4.3567. Min Act: -0.1700
Data Index: 2127183 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6692. Min Range: -4.6692
Max Act: 4.3254. Min Act: -0.1700
Data Index: 151671 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19