Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3960 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0603. Min Range: -4.0603
Max Act: 4.0603. Min Act: -0.1700
Data Index: 6416485 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0603. Min Range: -4.0603
Max Act: 3.9352. Min Act: -0.1700
Data Index: 7286670 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0603. Min Range: -4.0603
Max Act: 3.9040. Min Act: -0.1700
Data Index: 924644 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0603. Min Range: -4.0603
Max Act: 3.9040. Min Act: -0.1700
Data Index: 4702939 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0603. Min Range: -4.0603
Max Act: 3.8727. Min Act: -0.1700
Data Index: 7655052 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0603. Min Range: -4.0603
Max Act: 3.8414. Min Act: -0.1700
Data Index: 1119652 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0603. Min Range: -4.0603
Max Act: 3.8727. Min Act: -0.1700
Data Index: 6346622 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0603. Min Range: -4.0603
Max Act: 3.7789. Min Act: -0.1700
Data Index: 6251757 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0603. Min Range: -4.0603
Max Act: 3.7789. Min Act: -0.1700
Data Index: 7060292 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0603. Min Range: -4.0603
Max Act: 3.7476. Min Act: -0.1700
Data Index: 1984433 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0603. Min Range: -4.0603
Max Act: 3.7476. Min Act: -0.1700
Data Index: 1985226 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0603. Min Range: -4.0603
Max Act: 3.7163. Min Act: -0.1700
Data Index: 5758968 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0603. Min Range: -4.0603
Max Act: 3.7320. Min Act: -0.1700
Data Index: 769622 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0603. Min Range: -4.0603
Max Act: 3.7320. Min Act: -0.1700
Data Index: 4347651 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0603. Min Range: -4.0603
Max Act: 3.7476. Min Act: -0.1700
Data Index: 369936 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0603. Min Range: -4.0603
Max Act: 3.7320. Min Act: -0.1700
Data Index: 3782370 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0603. Min Range: -4.0603
Max Act: 3.7163. Min Act: -0.1700
Data Index: 5512852 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0603. Min Range: -4.0603
Max Act: 3.7007. Min Act: -0.1700
Data Index: 2148586 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0603. Min Range: -4.0603
Max Act: 3.7163. Min Act: -0.1700
Data Index: 6807840 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0603. Min Range: -4.0603
Max Act: 3.6850. Min Act: -0.1700
Data Index: 415744 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19