Model: None
Dataset: The Pile
Neuron 4031 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.5436. Min Act: -0.1700
Data Index: 3189200 (The Pile)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.4810. Min Act: -0.1700
Data Index: 2720933 (The Pile)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.4339. Min Act: -0.1700
Data Index: 9628349 (The Pile)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.4339. Min Act: -0.1700
Data Index: 674219 (The Pile)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.4183. Min Act: -0.1700
Data Index: 3447715 (The Pile)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.4026. Min Act: -0.1700
Data Index: 585127 (The Pile)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.4026. Min Act: -0.1700
Data Index: 1249096 (The Pile)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.3869. Min Act: -0.1700
Data Index: 680964 (The Pile)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.3869. Min Act: -0.1700
Data Index: 7145357 (The Pile)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.3712. Min Act: -0.1700
Data Index: 768836 (The Pile)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.3712. Min Act: -0.1700
Data Index: 3847393 (The Pile)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.3712. Min Act: -0.1700
Data Index: 5476325 (The Pile)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.3712. Min Act: -0.1700
Data Index: 5590565 (The Pile)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.3555. Min Act: -0.1700
Data Index: 3450038 (The Pile)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.3555. Min Act: -0.1700
Data Index: 9007278 (The Pile)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.3555. Min Act: -0.1700
Data Index: 7971881 (The Pile)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.3555. Min Act: -0.1699
Data Index: 5156745 (The Pile)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.3555. Min Act: -0.1700
Data Index: 7374566 (The Pile)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.3555. Min Act: -0.1700
Data Index: 5716272 (The Pile)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.3555. Min Act: -0.1700
Data Index: 8307833 (The Pile)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19