Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4802 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1374. Min Range: -8.1374
Max Act: 8.1374. Min Act: -0.1700
Data Index: 1905210 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1374. Min Range: -8.1374
Max Act: 8.0749. Min Act: -0.1700
Data Index: 1689272 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1374. Min Range: -8.1374
Max Act: 7.8561. Min Act: -0.1700
Data Index: 1617006 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1374. Min Range: -8.1374
Max Act: 7.7624. Min Act: -0.1700
Data Index: 5351674 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1374. Min Range: -8.1374
Max Act: 7.7624. Min Act: -0.1700
Data Index: 7270050 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1374. Min Range: -8.1374
Max Act: 7.7311. Min Act: -0.1700
Data Index: 2165587 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1374. Min Range: -8.1374
Max Act: 7.6999. Min Act: -0.1700
Data Index: 27026 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1374. Min Range: -8.1374
Max Act: 7.6999. Min Act: -0.1700
Data Index: 2875678 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1374. Min Range: -8.1374
Max Act: 7.6999. Min Act: -0.1700
Data Index: 2410845 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1374. Min Range: -8.1374
Max Act: 7.6686. Min Act: -0.1700
Data Index: 4210161 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1374. Min Range: -8.1374
Max Act: 7.6374. Min Act: -0.1700
Data Index: 6131319 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1374. Min Range: -8.1374
Max Act: 7.6061. Min Act: -0.1700
Data Index: 7741940 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1374. Min Range: -8.1374
Max Act: 7.6061. Min Act: -0.1700
Data Index: 6375069 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1374. Min Range: -8.1374
Max Act: 7.5749. Min Act: -0.1700
Data Index: 6159723 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1374. Min Range: -8.1374
Max Act: 7.5436. Min Act: -0.1700
Data Index: 3122206 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1374. Min Range: -8.1374
Max Act: 7.5749. Min Act: -0.1700
Data Index: 5014872 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1374. Min Range: -8.1374
Max Act: 7.5436. Min Act: -0.1700
Data Index: 5275151 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1374. Min Range: -8.1374
Max Act: 7.5436. Min Act: -0.1700
Data Index: 6739080 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1374. Min Range: -8.1374
Max Act: 7.5124. Min Act: -0.1700
Data Index: 1653902 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1374. Min Range: -8.1374
Max Act: 7.5124. Min Act: -0.1700
Data Index: 3821487 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #19