Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5538 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.0582. Min Range: -11.0582
Max Act: 11.0582. Min Act: -0.1700
Data Index: 2382034 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.0582. Min Range: -11.0582
Max Act: 10.9332. Min Act: -0.1700
Data Index: 2616047 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.0582. Min Range: -11.0582
Max Act: 10.6832. Min Act: -0.1700
Data Index: 3141413 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.0582. Min Range: -11.0582
Max Act: 10.6832. Min Act: -0.1700
Data Index: 8021584 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.0582. Min Range: -11.0582
Max Act: 10.6207. Min Act: -0.1700
Data Index: 7110366 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.0582. Min Range: -11.0582
Max Act: 10.4332. Min Act: -0.1700
Data Index: 1511590 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.0582. Min Range: -11.0582
Max Act: 10.4332. Min Act: -0.1700
Data Index: 2791318 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.0582. Min Range: -11.0582
Max Act: 10.4332. Min Act: -0.1700
Data Index: 5166931 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.0582. Min Range: -11.0582
Max Act: 10.3082. Min Act: -0.1700
Data Index: 4783011 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.0582. Min Range: -11.0582
Max Act: 10.3082. Min Act: -0.1700
Data Index: 6759690 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.0582. Min Range: -11.0582
Max Act: 10.1832. Min Act: -0.1700
Data Index: 8262639 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.0582. Min Range: -11.0582
Max Act: 10.2457. Min Act: -0.1700
Data Index: 5166932 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.0582. Min Range: -11.0582
Max Act: 10.1832. Min Act: -0.1700
Data Index: 8160659 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.0582. Min Range: -11.0582
Max Act: 10.1832. Min Act: -0.1700
Data Index: 7964709 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.0582. Min Range: -11.0582
Max Act: 9.9957. Min Act: -0.1700
Data Index: 6078198 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.0582. Min Range: -11.0582
Max Act: 9.9957. Min Act: -0.1700
Data Index: 3211336 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.0582. Min Range: -11.0582
Max Act: 9.9957. Min Act: -0.1700
Data Index: 8500754 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.0582. Min Range: -11.0582
Max Act: 9.9957. Min Act: -0.1700
Data Index: 3853602 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.0582. Min Range: -11.0582
Max Act: 9.9957. Min Act: -0.1700
Data Index: 921982 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.0582. Min Range: -11.0582
Max Act: 9.9332. Min Act: -0.1700
Data Index: 7613596 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #19