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

Dataset: The Pile

Neuron 245 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: 0.6440. Min Range: -0.6440

Max Act: 0.6440. Min Act: -0.0000

Data Index: 717141 (The Pile)

Max Activating Token Index: 803

Text #1

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.5452. Min Act: -0.0000

Data Index: 1508950 (The Pile)

Max Activating Token Index: 1014

Text #2

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.6207. Min Act: -0.0000

Data Index: 1265432 (The Pile)

Max Activating Token Index: 917

Text #3

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.5484. Min Act: -0.0000

Data Index: 973522 (The Pile)

Max Activating Token Index: 396

Text #4

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.5655. Min Act: -0.0000

Data Index: 445116 (The Pile)

Max Activating Token Index: 76

Text #5

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.5659. Min Act: -0.0000

Data Index: 339405 (The Pile)

Max Activating Token Index: 244

Text #6

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.5291. Min Act: -0.0000

Data Index: 1291065 (The Pile)

Max Activating Token Index: 710

Text #7

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4700. Min Act: -0.0000

Data Index: 1720428 (The Pile)

Max Activating Token Index: 534

Text #8

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.5137. Min Act: -0.0000

Data Index: 469571 (The Pile)

Max Activating Token Index: 849

Text #9

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.5507. Min Act: -0.0000

Data Index: 1366571 (The Pile)

Max Activating Token Index: 88

Text #10

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.6144. Min Act: -0.0000

Data Index: 695394 (The Pile)

Max Activating Token Index: 885

Text #11

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.5263. Min Act: -0.0000

Data Index: 1654143 (The Pile)

Max Activating Token Index: 511

Text #12

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4995. Min Act: -0.0000

Data Index: 1681263 (The Pile)

Max Activating Token Index: 447

Text #13

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.5341. Min Act: -0.0000

Data Index: 1926278 (The Pile)

Max Activating Token Index: 1003

Text #14

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.5297. Min Act: -0.0000

Data Index: 1061396 (The Pile)

Max Activating Token Index: 409

Text #15

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.5221. Min Act: -0.0000

Data Index: 567964 (The Pile)

Max Activating Token Index: 614

Text #16

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4903. Min Act: -0.0000

Data Index: 1144320 (The Pile)

Max Activating Token Index: 818

Text #17

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4826. Min Act: -0.0000

Data Index: 1573026 (The Pile)

Max Activating Token Index: 230

Text #18

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4795. Min Act: -0.0000

Data Index: 1682787 (The Pile)

Max Activating Token Index: 710

Text #19

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4926. Min Act: -0.0000

Data Index: 897497 (The Pile)

Max Activating Token Index: 66