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

Dataset: The Pile

Neuron 3064 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: 0.3141. Min Range: -0.3141

Max Act: 0.3141. Min Act: -0.0000

Data Index: 1195174 (The Pile)

Max Activating Token Index: 332

Text #1

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2822. Min Act: -0.0000

Data Index: 1772832 (The Pile)

Max Activating Token Index: 254

Text #2

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2693. Min Act: -0.0000

Data Index: 1736288 (The Pile)

Max Activating Token Index: 414

Text #3

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2622. Min Act: -0.0000

Data Index: 46936 (The Pile)

Max Activating Token Index: 839

Text #4

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2771. Min Act: -0.0000

Data Index: 126791 (The Pile)

Max Activating Token Index: 619

Text #5

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2617. Min Act: -0.0000

Data Index: 1441131 (The Pile)

Max Activating Token Index: 654

Text #6

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2491. Min Act: -0.0000

Data Index: 1947184 (The Pile)

Max Activating Token Index: 814

Text #7

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2450. Min Act: -0.0000

Data Index: 242704 (The Pile)

Max Activating Token Index: 809

Text #8

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2303. Min Act: -0.0000

Data Index: 1326615 (The Pile)

Max Activating Token Index: 763

Text #9

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2617. Min Act: -0.0000

Data Index: 1363425 (The Pile)

Max Activating Token Index: 589

Text #10

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2432. Min Act: -0.0000

Data Index: 1528464 (The Pile)

Max Activating Token Index: 653

Text #11

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2421. Min Act: -0.0000

Data Index: 225014 (The Pile)

Max Activating Token Index: 225

Text #12

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2249. Min Act: -0.0000

Data Index: 386136 (The Pile)

Max Activating Token Index: 18

Text #13

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2319. Min Act: -0.0000

Data Index: 363127 (The Pile)

Max Activating Token Index: 714

Text #14

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2205. Min Act: -0.0000

Data Index: 297936 (The Pile)

Max Activating Token Index: 68

Text #15

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2284. Min Act: -0.0000

Data Index: 64008 (The Pile)

Max Activating Token Index: 475

Text #16

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2347. Min Act: -0.0000

Data Index: 1678836 (The Pile)

Max Activating Token Index: 308

Text #17

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2118. Min Act: -0.0000

Data Index: 74319 (The Pile)

Max Activating Token Index: 375

Text #18

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2229. Min Act: -0.0000

Data Index: 1427545 (The Pile)

Max Activating Token Index: 853

Text #19

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2321. Min Act: -0.0000

Data Index: 1914573 (The Pile)

Max Activating Token Index: 880