Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4369 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2891. Min Act: -0.0000

Data Index: 1711191 (The Pile)

Max Activating Token Index: 801

Text #1

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2650. Min Act: -0.0000

Data Index: 26356 (The Pile)

Max Activating Token Index: 182

Text #2

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2515. Min Act: -0.0000

Data Index: 308490 (The Pile)

Max Activating Token Index: 995

Text #3

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2367. Min Act: -0.0000

Data Index: 399375 (The Pile)

Max Activating Token Index: 486

Text #4

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2442. Min Act: -0.0000

Data Index: 1038135 (The Pile)

Max Activating Token Index: 859

Text #5

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2747. Min Act: -0.0000

Data Index: 1943402 (The Pile)

Max Activating Token Index: 705

Text #6

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2320. Min Act: -0.0000

Data Index: 547415 (The Pile)

Max Activating Token Index: 642

Text #7

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2432. Min Act: -0.0000

Data Index: 1572583 (The Pile)

Max Activating Token Index: 43

Text #8

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2151. Min Act: -0.0000

Data Index: 1142027 (The Pile)

Max Activating Token Index: 619

Text #9

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2166. Min Act: -0.0000

Data Index: 1094471 (The Pile)

Max Activating Token Index: 121

Text #10

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2213. Min Act: -0.0000

Data Index: 970809 (The Pile)

Max Activating Token Index: 291

Text #11

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2114. Min Act: -0.0000

Data Index: 658581 (The Pile)

Max Activating Token Index: 32

Text #12

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2198. Min Act: -0.0000

Data Index: 1720961 (The Pile)

Max Activating Token Index: 102

Text #13

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2103. Min Act: -0.0000

Data Index: 1538976 (The Pile)

Max Activating Token Index: 741

Text #14

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.1961. Min Act: -0.0000

Data Index: 1238716 (The Pile)

Max Activating Token Index: 353

Text #15

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2319. Min Act: -0.0000

Data Index: 1663477 (The Pile)

Max Activating Token Index: 121

Text #16

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2326. Min Act: -0.0000

Data Index: 870473 (The Pile)

Max Activating Token Index: 777

Text #17

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2505. Min Act: -0.0000

Data Index: 176264 (The Pile)

Max Activating Token Index: 889

Text #18

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2099. Min Act: -0.0000

Data Index: 927721 (The Pile)

Max Activating Token Index: 631

Text #19

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.1918. Min Act: -0.0000

Data Index: 46492 (The Pile)

Max Activating Token Index: 322