Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3859 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8783. Min Range: -2.8783
Max Act: 2.8624. Min Act: -0.1700
Data Index: 7699532 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8783. Min Range: -2.8783
Max Act: 2.8783. Min Act: -0.1700
Data Index: 1559191 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8783. Min Range: -2.8783
Max Act: 2.7350. Min Act: -0.1700
Data Index: 3084024 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8783. Min Range: -2.8783
Max Act: 2.7509. Min Act: -0.1700
Data Index: 3420216 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8783. Min Range: -2.8783
Max Act: 2.7350. Min Act: -0.1700
Data Index: 157523 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8783. Min Range: -2.8783
Max Act: 2.7350. Min Act: -0.1700
Data Index: 6479763 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8783. Min Range: -2.8783
Max Act: 2.7190. Min Act: -0.1700
Data Index: 6343862 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8783. Min Range: -2.8783
Max Act: 2.6870. Min Act: -0.1700
Data Index: 4502936 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8783. Min Range: -2.8783
Max Act: 2.6710. Min Act: -0.1700
Data Index: 2090051 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8783. Min Range: -2.8783
Max Act: 2.6710. Min Act: -0.1700
Data Index: 4277691 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8783. Min Range: -2.8783
Max Act: 2.6710. Min Act: -0.1700
Data Index: 4464322 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8783. Min Range: -2.8783
Max Act: 2.6549. Min Act: -0.1700
Data Index: 2512726 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8783. Min Range: -2.8783
Max Act: 2.6710. Min Act: -0.1700
Data Index: 1161142 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8783. Min Range: -2.8783
Max Act: 2.6710. Min Act: -0.1700
Data Index: 3136680 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8783. Min Range: -2.8783
Max Act: 2.6870. Min Act: -0.1700
Data Index: 3055392 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8783. Min Range: -2.8783
Max Act: 2.6710. Min Act: -0.1700
Data Index: 1766819 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8783. Min Range: -2.8783
Max Act: 2.6549. Min Act: -0.1700
Data Index: 4446653 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8783. Min Range: -2.8783
Max Act: 2.6549. Min Act: -0.1700
Data Index: 2115497 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8783. Min Range: -2.8783
Max Act: 2.6549. Min Act: -0.1700
Data Index: 959451 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8783. Min Range: -2.8783
Max Act: 2.6389. Min Act: -0.1700
Data Index: 5670684 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #19