Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2500 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.4633. Min Range: -7.4633
Max Act: 7.4633. Min Act: -0.1700
Data Index: 7178135 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4633. Min Range: -7.4633
Max Act: 7.2758. Min Act: -0.1700
Data Index: 1897058 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4633. Min Range: -7.4633
Max Act: 7.2758. Min Act: -0.1700
Data Index: 3530974 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4633. Min Range: -7.4633
Max Act: 7.2133. Min Act: -0.1700
Data Index: 1211374 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4633. Min Range: -7.4633
Max Act: 7.2133. Min Act: -0.1700
Data Index: 7833911 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4633. Min Range: -7.4633
Max Act: 7.1196. Min Act: -0.1700
Data Index: 7236253 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4633. Min Range: -7.4633
Max Act: 7.1508. Min Act: -0.1700
Data Index: 3207016 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4633. Min Range: -7.4633
Max Act: 7.1196. Min Act: -0.1700
Data Index: 2967676 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4633. Min Range: -7.4633
Max Act: 7.1196. Min Act: -0.1700
Data Index: 2412815 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4633. Min Range: -7.4633
Max Act: 7.1196. Min Act: -0.1700
Data Index: 2654077 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4633. Min Range: -7.4633
Max Act: 7.0883. Min Act: -0.1700
Data Index: 770274 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4633. Min Range: -7.4633
Max Act: 7.0571. Min Act: -0.1700
Data Index: 2918103 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4633. Min Range: -7.4633
Max Act: 7.0571. Min Act: -0.1700
Data Index: 5121207 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4633. Min Range: -7.4633
Max Act: 7.0571. Min Act: -0.1700
Data Index: 204482 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4633. Min Range: -7.4633
Max Act: 7.0571. Min Act: -0.1700
Data Index: 4744516 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4633. Min Range: -7.4633
Max Act: 7.0258. Min Act: -0.1700
Data Index: 7438555 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4633. Min Range: -7.4633
Max Act: 7.0258. Min Act: -0.1700
Data Index: 2034387 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4633. Min Range: -7.4633
Max Act: 7.0258. Min Act: -0.1700
Data Index: 7009583 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4633. Min Range: -7.4633
Max Act: 6.9946. Min Act: -0.1700
Data Index: 1028782 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4633. Min Range: -7.4633
Max Act: 7.0258. Min Act: -0.1700
Data Index: 1131841 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #19