Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2862 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2290. Min Range: -4.2290
Max Act: 4.2290. Min Act: -0.1700
Data Index: 7180602 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2290. Min Range: -4.2290
Max Act: 4.1978. Min Act: -0.1700
Data Index: 7790740 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2290. Min Range: -4.2290
Max Act: 4.1665. Min Act: -0.1700
Data Index: 8661965 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2290. Min Range: -4.2290
Max Act: 4.1353. Min Act: -0.1700
Data Index: 1169743 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2290. Min Range: -4.2290
Max Act: 4.0728. Min Act: -0.1700
Data Index: 3478612 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2290. Min Range: -4.2290
Max Act: 4.0415. Min Act: -0.1700
Data Index: 6090318 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2290. Min Range: -4.2290
Max Act: 4.0415. Min Act: -0.1700
Data Index: 8228096 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2290. Min Range: -4.2290
Max Act: 4.0728. Min Act: -0.1700
Data Index: 6904431 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2290. Min Range: -4.2290
Max Act: 4.0415. Min Act: -0.1700
Data Index: 8671055 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2290. Min Range: -4.2290
Max Act: 3.9790. Min Act: -0.1700
Data Index: 2426124 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2290. Min Range: -4.2290
Max Act: 3.9790. Min Act: -0.1700
Data Index: 790366 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2290. Min Range: -4.2290
Max Act: 4.0102. Min Act: -0.1700
Data Index: 219388 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2290. Min Range: -4.2290
Max Act: 3.9477. Min Act: -0.1700
Data Index: 6473814 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2290. Min Range: -4.2290
Max Act: 3.9790. Min Act: -0.1700
Data Index: 2038611 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2290. Min Range: -4.2290
Max Act: 3.9790. Min Act: -0.1700
Data Index: 8298003 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2290. Min Range: -4.2290
Max Act: 3.9165. Min Act: -0.1700
Data Index: 6339129 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2290. Min Range: -4.2290
Max Act: 3.8852. Min Act: -0.1700
Data Index: 7790089 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2290. Min Range: -4.2290
Max Act: 3.9165. Min Act: -0.1700
Data Index: 4454272 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2290. Min Range: -4.2290
Max Act: 3.9165. Min Act: -0.1700
Data Index: 5235629 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2290. Min Range: -4.2290
Max Act: 3.9165. Min Act: -0.1700
Data Index: 2502036 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #19