Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3039 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4594. Min Range: -5.4594
Max Act: 5.4594. Min Act: -0.1700
Data Index: 3868756 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4594. Min Range: -5.4594
Max Act: 5.4281. Min Act: -0.1700
Data Index: 3868789 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4594. Min Range: -5.4594
Max Act: 5.1469. Min Act: -0.1700
Data Index: 6742448 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4594. Min Range: -5.4594
Max Act: 5.1469. Min Act: -0.1700
Data Index: 1917948 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4594. Min Range: -5.4594
Max Act: 5.0844. Min Act: -0.1700
Data Index: 3125350 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4594. Min Range: -5.4594
Max Act: 5.0844. Min Act: -0.1700
Data Index: 6393852 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4594. Min Range: -5.4594
Max Act: 5.0531. Min Act: -0.1700
Data Index: 8282465 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4594. Min Range: -5.4594
Max Act: 5.0219. Min Act: -0.1700
Data Index: 986470 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4594. Min Range: -5.4594
Max Act: 4.9906. Min Act: -0.1700
Data Index: 6742444 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4594. Min Range: -5.4594
Max Act: 4.9906. Min Act: -0.1700
Data Index: 7756481 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4594. Min Range: -5.4594
Max Act: 4.9906. Min Act: -0.1700
Data Index: 7592694 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4594. Min Range: -5.4594
Max Act: 4.9594. Min Act: -0.1700
Data Index: 8802285 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4594. Min Range: -5.4594
Max Act: 4.9594. Min Act: -0.1700
Data Index: 8694488 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4594. Min Range: -5.4594
Max Act: 4.9594. Min Act: -0.1700
Data Index: 393681 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4594. Min Range: -5.4594
Max Act: 4.9281. Min Act: -0.1700
Data Index: 3125354 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4594. Min Range: -5.4594
Max Act: 4.9281. Min Act: -0.1700
Data Index: 7486363 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4594. Min Range: -5.4594
Max Act: 4.9281. Min Act: -0.1700
Data Index: 1192064 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4594. Min Range: -5.4594
Max Act: 4.9281. Min Act: -0.1700
Data Index: 6485957 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4594. Min Range: -5.4594
Max Act: 4.8969. Min Act: -0.1700
Data Index: 1850206 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4594. Min Range: -5.4594
Max Act: 4.9281. Min Act: -0.1700
Data Index: 3125345 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #19