Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4949 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2822. Min Range: -5.2822
Max Act: 5.2822. Min Act: -0.1700
Data Index: 939068 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2822. Min Range: -5.2822
Max Act: 5.1885. Min Act: -0.1700
Data Index: 7771311 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2822. Min Range: -5.2822
Max Act: 5.0947. Min Act: -0.1700
Data Index: 933638 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2822. Min Range: -5.2822
Max Act: 5.0010. Min Act: -0.1700
Data Index: 4662901 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2822. Min Range: -5.2822
Max Act: 5.0010. Min Act: -0.1700
Data Index: 363589 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2822. Min Range: -5.2822
Max Act: 4.9072. Min Act: -0.1700
Data Index: 363591 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2822. Min Range: -5.2822
Max Act: 4.9385. Min Act: -0.1700
Data Index: 1313719 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2822. Min Range: -5.2822
Max Act: 4.8760. Min Act: -0.1700
Data Index: 5422372 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2822. Min Range: -5.2822
Max Act: 4.8760. Min Act: -0.1700
Data Index: 4118558 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2822. Min Range: -5.2822
Max Act: 4.8447. Min Act: -0.1700
Data Index: 335763 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2822. Min Range: -5.2822
Max Act: 4.8135. Min Act: -0.1700
Data Index: 64462 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2822. Min Range: -5.2822
Max Act: 4.7822. Min Act: -0.1700
Data Index: 4677415 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2822. Min Range: -5.2822
Max Act: 4.7822. Min Act: -0.1700
Data Index: 6554833 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2822. Min Range: -5.2822
Max Act: 4.7510. Min Act: -0.1700
Data Index: 925011 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2822. Min Range: -5.2822
Max Act: 4.7510. Min Act: -0.1700
Data Index: 5679284 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2822. Min Range: -5.2822
Max Act: 4.7197. Min Act: -0.1700
Data Index: 957671 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2822. Min Range: -5.2822
Max Act: 4.7197. Min Act: -0.1700
Data Index: 1665910 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2822. Min Range: -5.2822
Max Act: 4.6572. Min Act: -0.1700
Data Index: 5796321 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2822. Min Range: -5.2822
Max Act: 4.6885. Min Act: -0.1700
Data Index: 2374732 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2822. Min Range: -5.2822
Max Act: 4.6885. Min Act: -0.1700
Data Index: 6134395 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #19