Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2254 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9564. Min Range: -7.9564
Max Act: 7.9564. Min Act: -0.1700
Data Index: 7337080 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9564. Min Range: -7.9564
Max Act: 7.7377. Min Act: -0.1700
Data Index: 1858354 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9564. Min Range: -7.9564
Max Act: 7.6752. Min Act: -0.1700
Data Index: 4168207 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9564. Min Range: -7.9564
Max Act: 7.6127. Min Act: -0.1700
Data Index: 1644793 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9564. Min Range: -7.9564
Max Act: 7.5814. Min Act: -0.1700
Data Index: 8058012 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9564. Min Range: -7.9564
Max Act: 7.4877. Min Act: -0.1700
Data Index: 4778864 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9564. Min Range: -7.9564
Max Act: 7.4877. Min Act: -0.1700
Data Index: 2743714 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9564. Min Range: -7.9564
Max Act: 7.3627. Min Act: -0.1700
Data Index: 5111181 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9564. Min Range: -7.9564
Max Act: 7.3627. Min Act: -0.1700
Data Index: 2190817 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9564. Min Range: -7.9564
Max Act: 7.3002. Min Act: -0.1700
Data Index: 8085224 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9564. Min Range: -7.9564
Max Act: 7.2377. Min Act: -0.1700
Data Index: 526169 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9564. Min Range: -7.9564
Max Act: 7.2377. Min Act: -0.1700
Data Index: 6166476 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9564. Min Range: -7.9564
Max Act: 7.2377. Min Act: -0.1700
Data Index: 6801916 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9564. Min Range: -7.9564
Max Act: 7.2377. Min Act: -0.1700
Data Index: 2625444 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9564. Min Range: -7.9564
Max Act: 7.1752. Min Act: -0.1700
Data Index: 4806061 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9564. Min Range: -7.9564
Max Act: 7.0814. Min Act: -0.1700
Data Index: 3357890 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9564. Min Range: -7.9564
Max Act: 7.1127. Min Act: -0.1700
Data Index: 5271872 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9564. Min Range: -7.9564
Max Act: 7.1127. Min Act: -0.1700
Data Index: 2081760 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9564. Min Range: -7.9564
Max Act: 7.0814. Min Act: -0.1700
Data Index: 6224483 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9564. Min Range: -7.9564
Max Act: 7.0814. Min Act: -0.1700
Data Index: 6997605 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #19