Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4754 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 64.9272. Min Range: -64.9272
Max Act: 64.9272. Min Act: -0.1700
Data Index: 2449260 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 64.9272. Min Range: -64.9272
Max Act: 64.9272. Min Act: -0.1700
Data Index: 5572136 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 64.9272. Min Range: -64.9272
Max Act: 64.1772. Min Act: -0.1700
Data Index: 4863591 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 64.9272. Min Range: -64.9272
Max Act: 63.9272. Min Act: -0.1700
Data Index: 594112 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 64.9272. Min Range: -64.9272
Max Act: 63.9272. Min Act: -0.1700
Data Index: 6656747 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 64.9272. Min Range: -64.9272
Max Act: 63.9272. Min Act: -0.1700
Data Index: 5798627 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 64.9272. Min Range: -64.9272
Max Act: 63.9272. Min Act: -0.1700
Data Index: 4040371 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 64.9272. Min Range: -64.9272
Max Act: 63.9272. Min Act: -0.1700
Data Index: 2227447 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 64.9272. Min Range: -64.9272
Max Act: 63.9272. Min Act: -0.1700
Data Index: 1895475 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 64.9272. Min Range: -64.9272
Max Act: 63.9272. Min Act: -0.1700
Data Index: 6712252 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 64.9272. Min Range: -64.9272
Max Act: 63.9272. Min Act: -0.1700
Data Index: 5799640 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 64.9272. Min Range: -64.9272
Max Act: 63.6772. Min Act: -0.1700
Data Index: 5044839 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 64.9272. Min Range: -64.9272
Max Act: 63.6772. Min Act: -0.1700
Data Index: 1613608 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 64.9272. Min Range: -64.9272
Max Act: 63.6772. Min Act: -0.1700
Data Index: 6836519 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 64.9272. Min Range: -64.9272
Max Act: 63.6772. Min Act: -0.1700
Data Index: 5791417 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 64.9272. Min Range: -64.9272
Max Act: 63.4272. Min Act: -0.1700
Data Index: 1237639 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 64.9272. Min Range: -64.9272
Max Act: 63.4272. Min Act: -0.1700
Data Index: 53076 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 64.9272. Min Range: -64.9272
Max Act: 63.4272. Min Act: -0.1700
Data Index: 2621719 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 64.9272. Min Range: -64.9272
Max Act: 63.4272. Min Act: -0.1700
Data Index: 3958388 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 64.9272. Min Range: -64.9272
Max Act: 63.4272. Min Act: -0.1700
Data Index: 339594 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #19