Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6246 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4618. Min Range: -8.4618
Max Act: 8.4618. Min Act: -0.1700
Data Index: 6263947 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4618. Min Range: -8.4618
Max Act: 7.8368. Min Act: -0.1700
Data Index: 4503243 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4618. Min Range: -8.4618
Max Act: 7.7743. Min Act: -0.1700
Data Index: 3845611 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4618. Min Range: -8.4618
Max Act: 7.7118. Min Act: -0.1700
Data Index: 598165 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4618. Min Range: -8.4618
Max Act: 7.6806. Min Act: -0.1700
Data Index: 1440638 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4618. Min Range: -8.4618
Max Act: 7.6493. Min Act: -0.1700
Data Index: 965889 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4618. Min Range: -8.4618
Max Act: 7.6493. Min Act: -0.1700
Data Index: 1924182 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4618. Min Range: -8.4618
Max Act: 7.6806. Min Act: -0.1700
Data Index: 7480786 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4618. Min Range: -8.4618
Max Act: 7.6493. Min Act: -0.1700
Data Index: 4719346 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4618. Min Range: -8.4618
Max Act: 7.6181. Min Act: -0.1700
Data Index: 6807211 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4618. Min Range: -8.4618
Max Act: 7.5868. Min Act: -0.1700
Data Index: 3547601 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4618. Min Range: -8.4618
Max Act: 7.5868. Min Act: -0.1700
Data Index: 2487073 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4618. Min Range: -8.4618
Max Act: 7.5868. Min Act: -0.1700
Data Index: 8818784 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4618. Min Range: -8.4618
Max Act: 7.5868. Min Act: -0.1700
Data Index: 6026612 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4618. Min Range: -8.4618
Max Act: 7.5556. Min Act: -0.1700
Data Index: 6470158 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4618. Min Range: -8.4618
Max Act: 7.5243. Min Act: -0.1700
Data Index: 1622364 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4618. Min Range: -8.4618
Max Act: 7.5556. Min Act: -0.1700
Data Index: 5110745 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4618. Min Range: -8.4618
Max Act: 7.5556. Min Act: -0.1700
Data Index: 488207 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4618. Min Range: -8.4618
Max Act: 7.5243. Min Act: -0.1700
Data Index: 5969181 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4618. Min Range: -8.4618
Max Act: 7.5556. Min Act: -0.1700
Data Index: 7887562 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #19