Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 773 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6645. Min Range: -5.6645
Max Act: 5.6645. Min Act: -0.1700
Data Index: 3554469 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6645. Min Range: -5.6645
Max Act: 5.5395. Min Act: -0.1700
Data Index: 821243 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6645. Min Range: -5.6645
Max Act: 5.2895. Min Act: -0.1700
Data Index: 8226437 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6645. Min Range: -5.6645
Max Act: 5.2270. Min Act: -0.1700
Data Index: 1082772 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6645. Min Range: -5.6645
Max Act: 5.1645. Min Act: -0.1700
Data Index: 4754958 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6645. Min Range: -5.6645
Max Act: 5.1333. Min Act: -0.1700
Data Index: 3991988 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6645. Min Range: -5.6645
Max Act: 5.1645. Min Act: -0.1700
Data Index: 5498 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6645. Min Range: -5.6645
Max Act: 5.1020. Min Act: -0.1700
Data Index: 4078072 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6645. Min Range: -5.6645
Max Act: 5.1020. Min Act: -0.1700
Data Index: 2979362 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6645. Min Range: -5.6645
Max Act: 5.0395. Min Act: -0.1700
Data Index: 1729973 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6645. Min Range: -5.6645
Max Act: 4.9770. Min Act: -0.1700
Data Index: 352563 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6645. Min Range: -5.6645
Max Act: 4.9458. Min Act: -0.1700
Data Index: 3099674 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6645. Min Range: -5.6645
Max Act: 4.9145. Min Act: -0.1700
Data Index: 2734826 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6645. Min Range: -5.6645
Max Act: 4.9458. Min Act: -0.1700
Data Index: 821245 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6645. Min Range: -5.6645
Max Act: 4.8520. Min Act: -0.1700
Data Index: 3415746 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6645. Min Range: -5.6645
Max Act: 4.8833. Min Act: -0.1700
Data Index: 1059308 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6645. Min Range: -5.6645
Max Act: 4.8833. Min Act: -0.1700
Data Index: 3362124 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6645. Min Range: -5.6645
Max Act: 4.8833. Min Act: -0.1700
Data Index: 8145201 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6645. Min Range: -5.6645
Max Act: 4.8520. Min Act: -0.1700
Data Index: 7043089 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6645. Min Range: -5.6645
Max Act: 4.8520. Min Act: -0.1700
Data Index: 322858 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #19