Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3677 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6694. Min Range: -6.6694
Max Act: 6.6694. Min Act: -0.1700
Data Index: 1694697 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6694. Min Range: -6.6694
Max Act: 6.5444. Min Act: -0.1700
Data Index: 4235575 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6694. Min Range: -6.6694
Max Act: 6.5757. Min Act: -0.1700
Data Index: 2941874 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6694. Min Range: -6.6694
Max Act: 6.5444. Min Act: -0.1700
Data Index: 5737350 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6694. Min Range: -6.6694
Max Act: 6.5132. Min Act: -0.1700
Data Index: 4866337 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6694. Min Range: -6.6694
Max Act: 6.5132. Min Act: -0.1700
Data Index: 8594167 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6694. Min Range: -6.6694
Max Act: 6.5132. Min Act: -0.1700
Data Index: 8456471 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6694. Min Range: -6.6694
Max Act: 6.4819. Min Act: -0.1700
Data Index: 6583046 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6694. Min Range: -6.6694
Max Act: 6.4507. Min Act: -0.1700
Data Index: 1767792 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6694. Min Range: -6.6694
Max Act: 6.4507. Min Act: -0.1700
Data Index: 8553373 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6694. Min Range: -6.6694
Max Act: 6.3882. Min Act: -0.1700
Data Index: 7625224 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6694. Min Range: -6.6694
Max Act: 6.3257. Min Act: -0.1700
Data Index: 3687360 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6694. Min Range: -6.6694
Max Act: 6.2944. Min Act: -0.1700
Data Index: 7279948 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6694. Min Range: -6.6694
Max Act: 6.3257. Min Act: -0.1700
Data Index: 7579167 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6694. Min Range: -6.6694
Max Act: 6.2944. Min Act: -0.1700
Data Index: 2267938 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6694. Min Range: -6.6694
Max Act: 6.2632. Min Act: -0.1700
Data Index: 4960545 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6694. Min Range: -6.6694
Max Act: 6.2632. Min Act: -0.1700
Data Index: 2297409 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6694. Min Range: -6.6694
Max Act: 6.2007. Min Act: -0.1700
Data Index: 6137268 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6694. Min Range: -6.6694
Max Act: 6.2007. Min Act: -0.1700
Data Index: 90533 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6694. Min Range: -6.6694
Max Act: 6.2007. Min Act: -0.1700
Data Index: 686675 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19