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

Dataset: The Pile

Neuron 1028 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: 0.7399. Min Range: -0.7399

Max Act: 0.7399. Min Act: -0.0000

Data Index: 1688147 (The Pile)

Max Activating Token Index: 203

Text #1

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.7129. Min Act: -0.0000

Data Index: 192935 (The Pile)

Max Activating Token Index: 833

Text #2

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.7203. Min Act: -0.0000

Data Index: 131312 (The Pile)

Max Activating Token Index: 456

Text #3

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.6946. Min Act: -0.0000

Data Index: 950083 (The Pile)

Max Activating Token Index: 413

Text #4

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.6645. Min Act: -0.0000

Data Index: 537973 (The Pile)

Max Activating Token Index: 872

Text #5

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.7286. Min Act: -0.0000

Data Index: 1058938 (The Pile)

Max Activating Token Index: 175

Text #6

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.7067. Min Act: -0.0000

Data Index: 625267 (The Pile)

Max Activating Token Index: 475

Text #7

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.7116. Min Act: -0.0000

Data Index: 398512 (The Pile)

Max Activating Token Index: 632

Text #8

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.6924. Min Act: -0.0000

Data Index: 326672 (The Pile)

Max Activating Token Index: 294

Text #9

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.6319. Min Act: -0.0000

Data Index: 1984270 (The Pile)

Max Activating Token Index: 351

Text #10

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.6505. Min Act: -0.0000

Data Index: 506394 (The Pile)

Max Activating Token Index: 884

Text #11

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.6506. Min Act: -0.0000

Data Index: 1809019 (The Pile)

Max Activating Token Index: 640

Text #12

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.6315. Min Act: -0.0000

Data Index: 734642 (The Pile)

Max Activating Token Index: 937

Text #13

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.6511. Min Act: -0.0000

Data Index: 1664952 (The Pile)

Max Activating Token Index: 177

Text #14

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.6186. Min Act: -0.0000

Data Index: 1986207 (The Pile)

Max Activating Token Index: 994

Text #15

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.6417. Min Act: -0.0000

Data Index: 508679 (The Pile)

Max Activating Token Index: 592

Text #16

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.6213. Min Act: -0.0000

Data Index: 1883517 (The Pile)

Max Activating Token Index: 629

Text #17

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.6485. Min Act: -0.0000

Data Index: 1532652 (The Pile)

Max Activating Token Index: 904

Text #18

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.6264. Min Act: -0.0000

Data Index: 578796 (The Pile)

Max Activating Token Index: 687

Text #19

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.5811. Min Act: -0.0000

Data Index: 1011761 (The Pile)

Max Activating Token Index: 770