Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2770 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9714. Min Range: -7.9714
Max Act: 7.9714. Min Act: -0.1700
Data Index: 4662577 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9714. Min Range: -7.9714
Max Act: 7.7214. Min Act: -0.1700
Data Index: 8810270 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9714. Min Range: -7.9714
Max Act: 7.7214. Min Act: -0.1700
Data Index: 3967974 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9714. Min Range: -7.9714
Max Act: 7.4089. Min Act: -0.1700
Data Index: 6733576 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9714. Min Range: -7.9714
Max Act: 7.4089. Min Act: -0.1700
Data Index: 4181006 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9714. Min Range: -7.9714
Max Act: 7.1901. Min Act: -0.1700
Data Index: 1238442 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9714. Min Range: -7.9714
Max Act: 7.1901. Min Act: -0.1700
Data Index: 3141800 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9714. Min Range: -7.9714
Max Act: 7.1589. Min Act: -0.1700
Data Index: 4538593 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9714. Min Range: -7.9714
Max Act: 7.1276. Min Act: -0.1700
Data Index: 7771979 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9714. Min Range: -7.9714
Max Act: 7.1276. Min Act: -0.1700
Data Index: 8099828 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9714. Min Range: -7.9714
Max Act: 7.0964. Min Act: -0.1700
Data Index: 2902736 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9714. Min Range: -7.9714
Max Act: 7.0964. Min Act: -0.1700
Data Index: 7508362 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9714. Min Range: -7.9714
Max Act: 7.0339. Min Act: -0.1700
Data Index: 713079 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9714. Min Range: -7.9714
Max Act: 7.0339. Min Act: -0.1700
Data Index: 2519559 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9714. Min Range: -7.9714
Max Act: 7.0339. Min Act: -0.1700
Data Index: 6141877 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9714. Min Range: -7.9714
Max Act: 7.0026. Min Act: -0.1700
Data Index: 5191534 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9714. Min Range: -7.9714
Max Act: 7.0026. Min Act: -0.1700
Data Index: 2006611 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9714. Min Range: -7.9714
Max Act: 6.9401. Min Act: -0.1700
Data Index: 1214795 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9714. Min Range: -7.9714
Max Act: 6.9089. Min Act: -0.1700
Data Index: 6050144 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9714. Min Range: -7.9714
Max Act: 6.9089. Min Act: -0.1700
Data Index: 8819161 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #19