Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 818 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6230. Min Range: -7.6230
Max Act: 7.6230. Min Act: -0.1700
Data Index: 1611876 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6230. Min Range: -7.6230
Max Act: 7.2792. Min Act: -0.1700
Data Index: 4653991 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6230. Min Range: -7.6230
Max Act: 7.1855. Min Act: -0.1700
Data Index: 5744524 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6230. Min Range: -7.6230
Max Act: 7.2167. Min Act: -0.1700
Data Index: 3016847 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6230. Min Range: -7.6230
Max Act: 7.0917. Min Act: -0.1700
Data Index: 3464862 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6230. Min Range: -7.6230
Max Act: 7.0605. Min Act: -0.1700
Data Index: 1796828 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6230. Min Range: -7.6230
Max Act: 6.9980. Min Act: -0.1700
Data Index: 1163180 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6230. Min Range: -7.6230
Max Act: 6.9667. Min Act: -0.1700
Data Index: 5080219 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6230. Min Range: -7.6230
Max Act: 6.9980. Min Act: -0.1700
Data Index: 2006160 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6230. Min Range: -7.6230
Max Act: 6.9042. Min Act: -0.1700
Data Index: 5205317 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6230. Min Range: -7.6230
Max Act: 6.9042. Min Act: -0.1700
Data Index: 2387135 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6230. Min Range: -7.6230
Max Act: 6.9042. Min Act: -0.1700
Data Index: 7567863 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6230. Min Range: -7.6230
Max Act: 6.8730. Min Act: -0.1700
Data Index: 5160562 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6230. Min Range: -7.6230
Max Act: 6.8730. Min Act: -0.1700
Data Index: 2564765 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6230. Min Range: -7.6230
Max Act: 6.8417. Min Act: -0.1700
Data Index: 4640367 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6230. Min Range: -7.6230
Max Act: 6.8105. Min Act: -0.1700
Data Index: 8539318 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6230. Min Range: -7.6230
Max Act: 6.7792. Min Act: -0.1700
Data Index: 6385960 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6230. Min Range: -7.6230
Max Act: 6.7792. Min Act: -0.1700
Data Index: 1688532 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6230. Min Range: -7.6230
Max Act: 6.7792. Min Act: -0.1700
Data Index: 5876074 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6230. Min Range: -7.6230
Max Act: 6.7792. Min Act: -0.1700
Data Index: 2855105 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19