Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 553 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5895. Min Range: -3.5895
Max Act: 3.5895. Min Act: -0.1700
Data Index: 1960717 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5895. Min Range: -3.5895
Max Act: 3.5582. Min Act: -0.1700
Data Index: 3316455 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5895. Min Range: -3.5895
Max Act: 3.4642. Min Act: -0.1700
Data Index: 199358 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5895. Min Range: -3.5895
Max Act: 3.4956. Min Act: -0.1700
Data Index: 4643484 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5895. Min Range: -3.5895
Max Act: 3.4642. Min Act: -0.1700
Data Index: 2094681 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5895. Min Range: -3.5895
Max Act: 3.4956. Min Act: -0.1700
Data Index: 4084608 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5895. Min Range: -3.5895
Max Act: 3.4642. Min Act: -0.1700
Data Index: 4174331 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5895. Min Range: -3.5895
Max Act: 3.4642. Min Act: -0.1700
Data Index: 8569362 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5895. Min Range: -3.5895
Max Act: 3.4329. Min Act: -0.1700
Data Index: 7000963 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5895. Min Range: -3.5895
Max Act: 3.4329. Min Act: -0.1700
Data Index: 6833353 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5895. Min Range: -3.5895
Max Act: 3.4329. Min Act: -0.1700
Data Index: 568537 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5895. Min Range: -3.5895
Max Act: 3.4642. Min Act: -0.1700
Data Index: 552022 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5895. Min Range: -3.5895
Max Act: 3.4015. Min Act: -0.1700
Data Index: 3638475 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5895. Min Range: -3.5895
Max Act: 3.4172. Min Act: -0.1700
Data Index: 6438025 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5895. Min Range: -3.5895
Max Act: 3.4015. Min Act: -0.1700
Data Index: 1960444 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5895. Min Range: -3.5895
Max Act: 3.3859. Min Act: -0.1700
Data Index: 361178 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5895. Min Range: -3.5895
Max Act: 3.3545. Min Act: -0.1700
Data Index: 2576123 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5895. Min Range: -3.5895
Max Act: 3.3859. Min Act: -0.1700
Data Index: 1433581 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5895. Min Range: -3.5895
Max Act: 3.3702. Min Act: -0.1700
Data Index: 1994607 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5895. Min Range: -3.5895
Max Act: 3.3545. Min Act: -0.1700
Data Index: 4975376 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19