Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 45 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5465. Min Range: -6.5465
Max Act: 6.5465. Min Act: -0.1700
Data Index: 5107696 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5465. Min Range: -6.5465
Max Act: 5.9840. Min Act: -0.1700
Data Index: 3888250 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5465. Min Range: -6.5465
Max Act: 5.8590. Min Act: -0.1700
Data Index: 2248581 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5465. Min Range: -6.5465
Max Act: 5.8278. Min Act: -0.1700
Data Index: 1923115 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5465. Min Range: -6.5465
Max Act: 5.7653. Min Act: -0.1700
Data Index: 3550538 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5465. Min Range: -6.5465
Max Act: 5.7653. Min Act: -0.1700
Data Index: 5672696 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5465. Min Range: -6.5465
Max Act: 5.7965. Min Act: -0.1700
Data Index: 2415574 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5465. Min Range: -6.5465
Max Act: 5.7340. Min Act: -0.1700
Data Index: 2934032 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5465. Min Range: -6.5465
Max Act: 5.7340. Min Act: -0.1700
Data Index: 3111137 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5465. Min Range: -6.5465
Max Act: 5.7028. Min Act: -0.1700
Data Index: 3952393 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5465. Min Range: -6.5465
Max Act: 5.6715. Min Act: -0.1700
Data Index: 7587392 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5465. Min Range: -6.5465
Max Act: 5.6715. Min Act: -0.1700
Data Index: 3015188 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5465. Min Range: -6.5465
Max Act: 5.6715. Min Act: -0.1700
Data Index: 328001 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5465. Min Range: -6.5465
Max Act: 5.6403. Min Act: -0.1700
Data Index: 703185 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5465. Min Range: -6.5465
Max Act: 5.6715. Min Act: -0.1700
Data Index: 322385 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5465. Min Range: -6.5465
Max Act: 5.6715. Min Act: -0.1700
Data Index: 4524336 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5465. Min Range: -6.5465
Max Act: 5.6715. Min Act: -0.1700
Data Index: 8518142 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5465. Min Range: -6.5465
Max Act: 5.6403. Min Act: -0.1700
Data Index: 1544412 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5465. Min Range: -6.5465
Max Act: 5.6403. Min Act: -0.1700
Data Index: 8335272 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5465. Min Range: -6.5465
Max Act: 5.6403. Min Act: -0.1700
Data Index: 5315161 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #19