Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1590 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2141. Min Range: -3.2141
Max Act: 3.2141. Min Act: -0.1700
Data Index: 6464799 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2141. Min Range: -3.2141
Max Act: 3.1040. Min Act: -0.1700
Data Index: 3980468 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2141. Min Range: -3.2141
Max Act: 3.0567. Min Act: -0.1700
Data Index: 638707 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2141. Min Range: -3.2141
Max Act: 3.0093. Min Act: -0.1700
Data Index: 7729404 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2141. Min Range: -3.2141
Max Act: 2.9935. Min Act: -0.1700
Data Index: 4384428 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2141. Min Range: -3.2141
Max Act: 2.8667. Min Act: -0.1700
Data Index: 1241882 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2141. Min Range: -3.2141
Max Act: 2.8826. Min Act: -0.1700
Data Index: 7518429 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2141. Min Range: -3.2141
Max Act: 2.8826. Min Act: -0.1700
Data Index: 2245595 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2141. Min Range: -3.2141
Max Act: 2.8826. Min Act: -0.1700
Data Index: 2330487 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2141. Min Range: -3.2141
Max Act: 2.8509. Min Act: -0.1700
Data Index: 762324 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2141. Min Range: -3.2141
Max Act: 2.8350. Min Act: -0.1700
Data Index: 5034276 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2141. Min Range: -3.2141
Max Act: 2.8350. Min Act: -0.1700
Data Index: 5795885 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2141. Min Range: -3.2141
Max Act: 2.8350. Min Act: -0.1700
Data Index: 7784282 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2141. Min Range: -3.2141
Max Act: 2.8031. Min Act: -0.1700
Data Index: 4879780 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2141. Min Range: -3.2141
Max Act: 2.8031. Min Act: -0.1700
Data Index: 2762825 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2141. Min Range: -3.2141
Max Act: 2.7872. Min Act: -0.1700
Data Index: 6052902 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2141. Min Range: -3.2141
Max Act: 2.7872. Min Act: -0.1700
Data Index: 4794339 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2141. Min Range: -3.2141
Max Act: 2.8031. Min Act: -0.1700
Data Index: 4332253 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2141. Min Range: -3.2141
Max Act: 2.7872. Min Act: -0.1700
Data Index: 1187757 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2141. Min Range: -3.2141
Max Act: 2.8031. Min Act: -0.1700
Data Index: 7977408 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19