Model: None
Dataset: The Pile
Neuron 3332 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.2465. Min Range: -3.2465
Max Act: 3.2465. Min Act: -0.1700
Data Index: 8127328 (The Pile)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2465. Min Range: -3.2465
Max Act: 3.2308. Min Act: -0.1700
Data Index: 10166077 (The Pile)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2465. Min Range: -3.2465
Max Act: 3.2151. Min Act: -0.1700
Data Index: 4462383 (The Pile)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2465. Min Range: -3.2465
Max Act: 3.1521. Min Act: -0.1700
Data Index: 9188534 (The Pile)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2465. Min Range: -3.2465
Max Act: 3.1521. Min Act: -0.1700
Data Index: 8110277 (The Pile)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2465. Min Range: -3.2465
Max Act: 3.1521. Min Act: -0.1700
Data Index: 8977553 (The Pile)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2465. Min Range: -3.2465
Max Act: 3.1521. Min Act: -0.1700
Data Index: 10017454 (The Pile)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2465. Min Range: -3.2465
Max Act: 3.1364. Min Act: -0.1700
Data Index: 1524478 (The Pile)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2465. Min Range: -3.2465
Max Act: 3.1049. Min Act: -0.1700
Data Index: 10654969 (The Pile)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2465. Min Range: -3.2465
Max Act: 3.0891. Min Act: -0.1700
Data Index: 930399 (The Pile)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2465. Min Range: -3.2465
Max Act: 3.0891. Min Act: -0.1700
Data Index: 7196174 (The Pile)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2465. Min Range: -3.2465
Max Act: 3.0891. Min Act: -0.1700
Data Index: 4850758 (The Pile)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2465. Min Range: -3.2465
Max Act: 3.0891. Min Act: -0.1700
Data Index: 9285814 (The Pile)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2465. Min Range: -3.2465
Max Act: 3.0891. Min Act: -0.1700
Data Index: 8367799 (The Pile)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2465. Min Range: -3.2465
Max Act: 3.0891. Min Act: -0.1700
Data Index: 8860601 (The Pile)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2465. Min Range: -3.2465
Max Act: 3.0733. Min Act: -0.1700
Data Index: 933398 (The Pile)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2465. Min Range: -3.2465
Max Act: 3.0733. Min Act: -0.1700
Data Index: 6937718 (The Pile)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2465. Min Range: -3.2465
Max Act: 3.0417. Min Act: -0.1700
Data Index: 3931484 (The Pile)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2465. Min Range: -3.2465
Max Act: 3.0417. Min Act: -0.1700
Data Index: 6144688 (The Pile)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2465. Min Range: -3.2465
Max Act: 3.0417. Min Act: -0.1700
Data Index: 3844584 (The Pile)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19