Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1867 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.7105. Min Act: -0.1700
Data Index: 3690872 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.6167. Min Act: -0.1700
Data Index: 4343275 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.3980. Min Act: -0.1700
Data Index: 3146648 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.2417. Min Act: -0.1700
Data Index: 5500567 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.2417. Min Act: -0.1700
Data Index: 539902 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.2105. Min Act: -0.1700
Data Index: 7270071 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.1792. Min Act: -0.1700
Data Index: 3266868 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.1792. Min Act: -0.1700
Data Index: 5018032 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.1167. Min Act: -0.1700
Data Index: 3098957 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.1167. Min Act: -0.1700
Data Index: 5324324 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.1479. Min Act: -0.1700
Data Index: 4051352 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.1167. Min Act: -0.1700
Data Index: 6347114 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.1167. Min Act: -0.1700
Data Index: 3916308 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.0854. Min Act: -0.1700
Data Index: 2090301 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.1167. Min Act: -0.1700
Data Index: 4951860 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.1167. Min Act: -0.1700
Data Index: 3812475 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.0542. Min Act: -0.1700
Data Index: 8660925 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.0542. Min Act: -0.1700
Data Index: 6997078 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.0542. Min Act: -0.1700
Data Index: 7967744 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.0542. Min Act: -0.1700
Data Index: 6966932 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #19