Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3467 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5371. Min Range: -6.5371
Max Act: 6.5371. Min Act: -0.1700
Data Index: 2659291 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5371. Min Range: -6.5371
Max Act: 6.2246. Min Act: -0.1700
Data Index: 5373137 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5371. Min Range: -6.5371
Max Act: 6.1309. Min Act: -0.1700
Data Index: 8582052 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5371. Min Range: -6.5371
Max Act: 6.0996. Min Act: -0.1700
Data Index: 2779210 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5371. Min Range: -6.5371
Max Act: 6.0684. Min Act: -0.1700
Data Index: 4381288 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5371. Min Range: -6.5371
Max Act: 6.0684. Min Act: -0.1700
Data Index: 5775811 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5371. Min Range: -6.5371
Max Act: 6.0371. Min Act: -0.1700
Data Index: 2211353 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5371. Min Range: -6.5371
Max Act: 6.0371. Min Act: -0.1700
Data Index: 4279302 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5371. Min Range: -6.5371
Max Act: 6.0059. Min Act: -0.1700
Data Index: 8598011 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5371. Min Range: -6.5371
Max Act: 5.9746. Min Act: -0.1700
Data Index: 4507485 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5371. Min Range: -6.5371
Max Act: 5.9434. Min Act: -0.1700
Data Index: 3759628 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5371. Min Range: -6.5371
Max Act: 5.9434. Min Act: -0.1700
Data Index: 3301996 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5371. Min Range: -6.5371
Max Act: 5.9121. Min Act: -0.1700
Data Index: 4157229 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5371. Min Range: -6.5371
Max Act: 5.9121. Min Act: -0.1700
Data Index: 3713108 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5371. Min Range: -6.5371
Max Act: 5.8809. Min Act: -0.1700
Data Index: 935371 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5371. Min Range: -6.5371
Max Act: 5.8809. Min Act: -0.1700
Data Index: 1679574 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5371. Min Range: -6.5371
Max Act: 5.8809. Min Act: -0.1700
Data Index: 932082 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5371. Min Range: -6.5371
Max Act: 5.8184. Min Act: -0.1700
Data Index: 5809086 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5371. Min Range: -6.5371
Max Act: 5.8496. Min Act: -0.1700
Data Index: 8203596 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5371. Min Range: -6.5371
Max Act: 5.8184. Min Act: -0.1700
Data Index: 6784724 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #19