Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3846 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.8571. Min Range: -13.8571
Max Act: 13.8571. Min Act: -0.1700
Data Index: 6059617 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.8571. Min Range: -13.8571
Max Act: 13.6696. Min Act: -0.1700
Data Index: 4159623 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.8571. Min Range: -13.8571
Max Act: 13.6696. Min Act: -0.1700
Data Index: 2068383 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.8571. Min Range: -13.8571
Max Act: 13.6696. Min Act: -0.1700
Data Index: 4005271 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.8571. Min Range: -13.8571
Max Act: 13.5446. Min Act: -0.1700
Data Index: 5990952 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.8571. Min Range: -13.8571
Max Act: 13.4196. Min Act: -0.1700
Data Index: 3165874 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.8571. Min Range: -13.8571
Max Act: 13.3571. Min Act: -0.1700
Data Index: 3417488 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.8571. Min Range: -13.8571
Max Act: 13.3571. Min Act: -0.1700
Data Index: 95943 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.8571. Min Range: -13.8571
Max Act: 13.3571. Min Act: -0.1700
Data Index: 4105335 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.8571. Min Range: -13.8571
Max Act: 13.2946. Min Act: -0.1700
Data Index: 6734433 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.8571. Min Range: -13.8571
Max Act: 13.2321. Min Act: -0.1700
Data Index: 2235109 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.8571. Min Range: -13.8571
Max Act: 13.2946. Min Act: -0.1700
Data Index: 933147 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.8571. Min Range: -13.8571
Max Act: 13.2946. Min Act: -0.1700
Data Index: 1316276 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.8571. Min Range: -13.8571
Max Act: 13.2321. Min Act: -0.1700
Data Index: 2283433 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.8571. Min Range: -13.8571
Max Act: 13.1696. Min Act: -0.1700
Data Index: 5461936 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.8571. Min Range: -13.8571
Max Act: 13.1696. Min Act: -0.1700
Data Index: 7776997 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.8571. Min Range: -13.8571
Max Act: 13.1071. Min Act: -0.1700
Data Index: 2209501 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.8571. Min Range: -13.8571
Max Act: 13.1696. Min Act: -0.1700
Data Index: 2710850 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.8571. Min Range: -13.8571
Max Act: 13.1696. Min Act: -0.1700
Data Index: 4596287 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.8571. Min Range: -13.8571
Max Act: 13.2321. Min Act: -0.1700
Data Index: 1541543 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19