Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2859 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.1631. Min Range: -12.1631
Max Act: 12.1631. Min Act: -0.1699
Data Index: 6116435 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.1631. Min Range: -12.1631
Max Act: 11.8506. Min Act: -0.1700
Data Index: 5122509 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.1631. Min Range: -12.1631
Max Act: 11.7256. Min Act: -0.1700
Data Index: 3134706 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.1631. Min Range: -12.1631
Max Act: 11.5381. Min Act: -0.1700
Data Index: 3877601 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.1631. Min Range: -12.1631
Max Act: 11.4756. Min Act: -0.1700
Data Index: 6715414 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.1631. Min Range: -12.1631
Max Act: 11.2881. Min Act: -0.1700
Data Index: 3413848 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.1631. Min Range: -12.1631
Max Act: 11.2256. Min Act: -0.1700
Data Index: 8454307 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.1631. Min Range: -12.1631
Max Act: 11.2256. Min Act: -0.1700
Data Index: 5285042 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.1631. Min Range: -12.1631
Max Act: 11.2256. Min Act: -0.1700
Data Index: 923454 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.1631. Min Range: -12.1631
Max Act: 11.2256. Min Act: -0.1700
Data Index: 6900069 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.1631. Min Range: -12.1631
Max Act: 11.2256. Min Act: -0.1700
Data Index: 5415303 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.1631. Min Range: -12.1631
Max Act: 11.1006. Min Act: -0.1700
Data Index: 4881174 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.1631. Min Range: -12.1631
Max Act: 11.1006. Min Act: -0.1700
Data Index: 2422004 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.1631. Min Range: -12.1631
Max Act: 11.1006. Min Act: -0.1697
Data Index: 4975558 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.1631. Min Range: -12.1631
Max Act: 11.0381. Min Act: -0.1700
Data Index: 8240243 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.1631. Min Range: -12.1631
Max Act: 11.0381. Min Act: -0.1700
Data Index: 878058 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.1631. Min Range: -12.1631
Max Act: 11.0381. Min Act: -0.1700
Data Index: 5186664 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.1631. Min Range: -12.1631
Max Act: 11.0381. Min Act: -0.1700
Data Index: 6116437 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.1631. Min Range: -12.1631
Max Act: 10.9756. Min Act: -0.1700
Data Index: 6719711 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.1631. Min Range: -12.1631
Max Act: 10.9756. Min Act: -0.1700
Data Index: 5125574 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #19