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

Dataset: The Pile

Neuron 3005 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2532. Min Range: -1.2532

Max Act: 1.2532. Min Act: -0.0000

Data Index: 1735451 (The Pile)

Max Activating Token Index: 70

Text #1

Max Range: 1.2532. Min Range: -1.2532

Max Act: 1.0390. Min Act: -0.0000

Data Index: 1524326 (The Pile)

Max Activating Token Index: 854

Text #2

Max Range: 1.2532. Min Range: -1.2532

Max Act: 1.0128. Min Act: -0.0000

Data Index: 70745 (The Pile)

Max Activating Token Index: 301

Text #3

Max Range: 1.2532. Min Range: -1.2532

Max Act: 1.0005. Min Act: -0.0000

Data Index: 1998485 (The Pile)

Max Activating Token Index: 315

Text #4

Max Range: 1.2532. Min Range: -1.2532

Max Act: 1.0125. Min Act: -0.0000

Data Index: 1382978 (The Pile)

Max Activating Token Index: 502

Text #5

Max Range: 1.2532. Min Range: -1.2532

Max Act: 0.9532. Min Act: -0.0000

Data Index: 792780 (The Pile)

Max Activating Token Index: 359

Text #6

Max Range: 1.2532. Min Range: -1.2532

Max Act: 0.8880. Min Act: -0.0000

Data Index: 718542 (The Pile)

Max Activating Token Index: 935

Text #7

Max Range: 1.2532. Min Range: -1.2532

Max Act: 0.8714. Min Act: -0.0000

Data Index: 1084314 (The Pile)

Max Activating Token Index: 63

Text #8

Max Range: 1.2532. Min Range: -1.2532

Max Act: 0.8049. Min Act: -0.0000

Data Index: 1552510 (The Pile)

Max Activating Token Index: 945

Text #9

Max Range: 1.2532. Min Range: -1.2532

Max Act: 0.8157. Min Act: -0.0000

Data Index: 11832 (The Pile)

Max Activating Token Index: 229

Text #10

Max Range: 1.2532. Min Range: -1.2532

Max Act: 0.7461. Min Act: -0.0000

Data Index: 1007354 (The Pile)

Max Activating Token Index: 935

Text #11

Max Range: 1.2532. Min Range: -1.2532

Max Act: 0.7366. Min Act: -0.0000

Data Index: 1374346 (The Pile)

Max Activating Token Index: 736

Text #12

Max Range: 1.2532. Min Range: -1.2532

Max Act: 0.7299. Min Act: -0.0000

Data Index: 1591684 (The Pile)

Max Activating Token Index: 379

Text #13

Max Range: 1.2532. Min Range: -1.2532

Max Act: 0.7253. Min Act: -0.0000

Data Index: 1040341 (The Pile)

Max Activating Token Index: 382

Text #14

Max Range: 1.2532. Min Range: -1.2532

Max Act: 0.7355. Min Act: -0.0000

Data Index: 1806677 (The Pile)

Max Activating Token Index: 602

Text #15

Max Range: 1.2532. Min Range: -1.2532

Max Act: 0.7284. Min Act: -0.0000

Data Index: 651656 (The Pile)

Max Activating Token Index: 467

Text #16

Max Range: 1.2532. Min Range: -1.2532

Max Act: 0.6221. Min Act: -0.0000

Data Index: 242151 (The Pile)

Max Activating Token Index: 325

Text #17

Max Range: 1.2532. Min Range: -1.2532

Max Act: 0.6133. Min Act: -0.0000

Data Index: 606126 (The Pile)

Max Activating Token Index: 549

Text #18

Max Range: 1.2532. Min Range: -1.2532

Max Act: 0.5698. Min Act: -0.0000

Data Index: 821635 (The Pile)

Max Activating Token Index: 316

Text #19

Max Range: 1.2532. Min Range: -1.2532

Max Act: 0.5428. Min Act: -0.0000

Data Index: 1073556 (The Pile)

Max Activating Token Index: 59