Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2096 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3354. Min Range: -3.3354
Max Act: 3.3354. Min Act: -0.1700
Data Index: 1299850 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3354. Min Range: -3.3354
Max Act: 3.2726. Min Act: -0.1700
Data Index: 5379043 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3354. Min Range: -3.3354
Max Act: 3.2098. Min Act: -0.1700
Data Index: 4528266 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3354. Min Range: -3.3354
Max Act: 3.2412. Min Act: -0.1700
Data Index: 4445828 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3354. Min Range: -3.3354
Max Act: 3.1940. Min Act: -0.1700
Data Index: 7715512 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3354. Min Range: -3.3354
Max Act: 3.1940. Min Act: -0.1700
Data Index: 5215757 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3354. Min Range: -3.3354
Max Act: 3.1940. Min Act: -0.1700
Data Index: 668900 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3354. Min Range: -3.3354
Max Act: 3.1468. Min Act: -0.1700
Data Index: 4389885 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3354. Min Range: -3.3354
Max Act: 3.1311. Min Act: -0.1700
Data Index: 6519701 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3354. Min Range: -3.3354
Max Act: 3.1468. Min Act: -0.1700
Data Index: 7696215 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3354. Min Range: -3.3354
Max Act: 3.1468. Min Act: -0.1700
Data Index: 5720525 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3354. Min Range: -3.3354
Max Act: 3.1468. Min Act: -0.1700
Data Index: 1160344 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3354. Min Range: -3.3354
Max Act: 3.1468. Min Act: -0.1700
Data Index: 755889 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3354. Min Range: -3.3354
Max Act: 3.1153. Min Act: -0.1700
Data Index: 6350917 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3354. Min Range: -3.3354
Max Act: 3.1311. Min Act: -0.1700
Data Index: 8254260 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3354. Min Range: -3.3354
Max Act: 3.1311. Min Act: -0.1700
Data Index: 5215756 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3354. Min Range: -3.3354
Max Act: 3.1468. Min Act: -0.1700
Data Index: 5681045 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3354. Min Range: -3.3354
Max Act: 3.1468. Min Act: -0.1700
Data Index: 4690779 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3354. Min Range: -3.3354
Max Act: 3.1311. Min Act: -0.1700
Data Index: 2878211 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3354. Min Range: -3.3354
Max Act: 3.1153. Min Act: -0.1700
Data Index: 4285168 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #19