Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1444 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.4537. Min Act: -0.0000

Data Index: 54256 (The Pile)

Max Activating Token Index: 716

Text #1

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.4319. Min Act: -0.0000

Data Index: 158979 (The Pile)

Max Activating Token Index: 244

Text #2

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.4184. Min Act: -0.0000

Data Index: 321652 (The Pile)

Max Activating Token Index: 205

Text #3

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.4201. Min Act: -0.0000

Data Index: 1488042 (The Pile)

Max Activating Token Index: 675

Text #4

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.4306. Min Act: -0.0000

Data Index: 1043977 (The Pile)

Max Activating Token Index: 366

Text #5

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.4093. Min Act: -0.0000

Data Index: 1887039 (The Pile)

Max Activating Token Index: 1013

Text #6

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.4085. Min Act: -0.0000

Data Index: 976156 (The Pile)

Max Activating Token Index: 874

Text #7

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.4074. Min Act: -0.0000

Data Index: 361509 (The Pile)

Max Activating Token Index: 973

Text #8

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.3932. Min Act: -0.0000

Data Index: 822251 (The Pile)

Max Activating Token Index: 285

Text #9

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.3845. Min Act: -0.0000

Data Index: 1565915 (The Pile)

Max Activating Token Index: 199

Text #10

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.3729. Min Act: -0.0000

Data Index: 1575500 (The Pile)

Max Activating Token Index: 937

Text #11

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.3744. Min Act: -0.0000

Data Index: 991395 (The Pile)

Max Activating Token Index: 153

Text #12

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.3766. Min Act: -0.0000

Data Index: 169901 (The Pile)

Max Activating Token Index: 342

Text #13

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.3580. Min Act: -0.0000

Data Index: 1758084 (The Pile)

Max Activating Token Index: 198

Text #14

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.3795. Min Act: -0.0000

Data Index: 995286 (The Pile)

Max Activating Token Index: 542

Text #15

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.3693. Min Act: -0.0000

Data Index: 73810 (The Pile)

Max Activating Token Index: 479

Text #16

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.3520. Min Act: -0.0000

Data Index: 488938 (The Pile)

Max Activating Token Index: 867

Text #17

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.3577. Min Act: -0.0000

Data Index: 1278786 (The Pile)

Max Activating Token Index: 34

Text #18

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.3657. Min Act: -0.0000

Data Index: 1453706 (The Pile)

Max Activating Token Index: 55

Text #19

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.3513. Min Act: -0.0000

Data Index: 951640 (The Pile)

Max Activating Token Index: 161