Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1825 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4674. Min Range: -6.4674
Max Act: 6.4674. Min Act: -0.1700
Data Index: 272490 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4674. Min Range: -6.4674
Max Act: 6.1237. Min Act: -0.1700
Data Index: 6741460 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4674. Min Range: -6.4674
Max Act: 6.0612. Min Act: -0.1700
Data Index: 7993701 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4674. Min Range: -6.4674
Max Act: 6.0924. Min Act: -0.1700
Data Index: 4504538 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4674. Min Range: -6.4674
Max Act: 5.9987. Min Act: -0.1700
Data Index: 203747 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4674. Min Range: -6.4674
Max Act: 5.9987. Min Act: -0.1700
Data Index: 4618134 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4674. Min Range: -6.4674
Max Act: 5.9674. Min Act: -0.1700
Data Index: 6384985 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4674. Min Range: -6.4674
Max Act: 5.9674. Min Act: -0.1700
Data Index: 501799 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4674. Min Range: -6.4674
Max Act: 5.9987. Min Act: -0.1700
Data Index: 1145661 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4674. Min Range: -6.4674
Max Act: 5.9362. Min Act: -0.1700
Data Index: 5790652 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4674. Min Range: -6.4674
Max Act: 5.9362. Min Act: -0.1700
Data Index: 8588325 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4674. Min Range: -6.4674
Max Act: 5.9674. Min Act: -0.1700
Data Index: 2730845 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4674. Min Range: -6.4674
Max Act: 5.9362. Min Act: -0.1700
Data Index: 8698887 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4674. Min Range: -6.4674
Max Act: 5.9362. Min Act: -0.1700
Data Index: 1247798 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4674. Min Range: -6.4674
Max Act: 5.9362. Min Act: -0.1700
Data Index: 3950919 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4674. Min Range: -6.4674
Max Act: 5.9362. Min Act: -0.1700
Data Index: 6002167 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4674. Min Range: -6.4674
Max Act: 5.9049. Min Act: -0.1700
Data Index: 1199979 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4674. Min Range: -6.4674
Max Act: 5.9049. Min Act: -0.1700
Data Index: 7027177 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4674. Min Range: -6.4674
Max Act: 5.9049. Min Act: -0.1700
Data Index: 1679234 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4674. Min Range: -6.4674
Max Act: 5.9049. Min Act: -0.1700
Data Index: 3862030 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19