Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5358 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1792. Min Range: -6.1792
Max Act: 6.1792. Min Act: -0.1700
Data Index: 326927 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1792. Min Range: -6.1792
Max Act: 6.1792. Min Act: -0.1700
Data Index: 4579494 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1792. Min Range: -6.1792
Max Act: 6.1480. Min Act: -0.1700
Data Index: 5747556 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1792. Min Range: -6.1792
Max Act: 6.1167. Min Act: -0.1700
Data Index: 7217224 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1792. Min Range: -6.1792
Max Act: 6.0855. Min Act: -0.1700
Data Index: 5836045 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1792. Min Range: -6.1792
Max Act: 6.0855. Min Act: -0.1700
Data Index: 4135102 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1792. Min Range: -6.1792
Max Act: 6.0855. Min Act: -0.1700
Data Index: 7486173 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1792. Min Range: -6.1792
Max Act: 6.0855. Min Act: -0.1700
Data Index: 2089133 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1792. Min Range: -6.1792
Max Act: 6.0855. Min Act: -0.1700
Data Index: 3312837 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1792. Min Range: -6.1792
Max Act: 6.0542. Min Act: -0.1700
Data Index: 3033229 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1792. Min Range: -6.1792
Max Act: 6.0230. Min Act: -0.1700
Data Index: 4431890 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1792. Min Range: -6.1792
Max Act: 6.0230. Min Act: -0.1700
Data Index: 8691145 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1792. Min Range: -6.1792
Max Act: 5.9917. Min Act: -0.1700
Data Index: 7275070 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1792. Min Range: -6.1792
Max Act: 5.9917. Min Act: -0.1700
Data Index: 5180400 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1792. Min Range: -6.1792
Max Act: 5.9605. Min Act: -0.1700
Data Index: 274990 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1792. Min Range: -6.1792
Max Act: 5.9605. Min Act: -0.1700
Data Index: 8443260 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1792. Min Range: -6.1792
Max Act: 5.9605. Min Act: -0.1700
Data Index: 4133950 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1792. Min Range: -6.1792
Max Act: 5.9605. Min Act: -0.1700
Data Index: 5176508 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1792. Min Range: -6.1792
Max Act: 5.9292. Min Act: -0.1700
Data Index: 2384417 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1792. Min Range: -6.1792
Max Act: 5.9292. Min Act: -0.1700
Data Index: 5167782 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19