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

Dataset: The Pile

Neuron 1794 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: 1.3335. Min Range: -1.3335

Max Act: 1.3335. Min Act: -0.0000

Data Index: 1548922 (The Pile)

Max Activating Token Index: 250

Text #1

Max Range: 1.3335. Min Range: -1.3335

Max Act: 1.2332. Min Act: -0.0000

Data Index: 1973906 (The Pile)

Max Activating Token Index: 436

Text #2

Max Range: 1.3335. Min Range: -1.3335

Max Act: 1.0093. Min Act: -0.0000

Data Index: 764273 (The Pile)

Max Activating Token Index: 43

Text #3

Max Range: 1.3335. Min Range: -1.3335

Max Act: 1.0172. Min Act: -0.0000

Data Index: 1157495 (The Pile)

Max Activating Token Index: 169

Text #4

Max Range: 1.3335. Min Range: -1.3335

Max Act: 0.9401. Min Act: -0.0000

Data Index: 152910 (The Pile)

Max Activating Token Index: 471

Text #5

Max Range: 1.3335. Min Range: -1.3335

Max Act: 0.9603. Min Act: -0.0000

Data Index: 1116139 (The Pile)

Max Activating Token Index: 267

Text #6

Max Range: 1.3335. Min Range: -1.3335

Max Act: 0.9705. Min Act: -0.0000

Data Index: 922873 (The Pile)

Max Activating Token Index: 779

Text #7

Max Range: 1.3335. Min Range: -1.3335

Max Act: 0.9593. Min Act: -0.0000

Data Index: 807177 (The Pile)

Max Activating Token Index: 400

Text #8

Max Range: 1.3335. Min Range: -1.3335

Max Act: 0.8765. Min Act: -0.0000

Data Index: 1705486 (The Pile)

Max Activating Token Index: 687

Text #9

Max Range: 1.3335. Min Range: -1.3335

Max Act: 0.9178. Min Act: -0.0000

Data Index: 327689 (The Pile)

Max Activating Token Index: 801

Text #10

Max Range: 1.3335. Min Range: -1.3335

Max Act: 0.9297. Min Act: -0.0000

Data Index: 161300 (The Pile)

Max Activating Token Index: 853

Text #11

Max Range: 1.3335. Min Range: -1.3335

Max Act: 0.9411. Min Act: -0.0000

Data Index: 923645 (The Pile)

Max Activating Token Index: 491

Text #12

Max Range: 1.3335. Min Range: -1.3335

Max Act: 0.8453. Min Act: -0.0000

Data Index: 1411426 (The Pile)

Max Activating Token Index: 911

Text #13

Max Range: 1.3335. Min Range: -1.3335

Max Act: 0.9079. Min Act: -0.0000

Data Index: 325161 (The Pile)

Max Activating Token Index: 462

Text #14

Max Range: 1.3335. Min Range: -1.3335

Max Act: 0.8972. Min Act: -0.0000

Data Index: 267771 (The Pile)

Max Activating Token Index: 599

Text #15

Max Range: 1.3335. Min Range: -1.3335

Max Act: 0.8907. Min Act: -0.0000

Data Index: 1581278 (The Pile)

Max Activating Token Index: 947

Text #16

Max Range: 1.3335. Min Range: -1.3335

Max Act: 0.8599. Min Act: -0.0000

Data Index: 64717 (The Pile)

Max Activating Token Index: 997

Text #17

Max Range: 1.3335. Min Range: -1.3335

Max Act: 0.8297. Min Act: -0.0000

Data Index: 678065 (The Pile)

Max Activating Token Index: 321

Text #18

Max Range: 1.3335. Min Range: -1.3335

Max Act: 0.8224. Min Act: -0.0000

Data Index: 1240024 (The Pile)

Max Activating Token Index: 330

Text #19

Max Range: 1.3335. Min Range: -1.3335

Max Act: 0.8207. Min Act: -0.0000

Data Index: 1366839 (The Pile)

Max Activating Token Index: 452