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

Dataset: The Pile

Neuron 4548 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: 0.6131. Min Range: -0.6131

Max Act: 0.6008. Min Act: -0.0000

Data Index: 632291 (The Pile)

Max Activating Token Index: 196

Text #1

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.6131. Min Act: -0.0000

Data Index: 43869 (The Pile)

Max Activating Token Index: 631

Text #2

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.4656. Min Act: -0.0000

Data Index: 1300429 (The Pile)

Max Activating Token Index: 947

Text #3

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.5554. Min Act: -0.0000

Data Index: 1841327 (The Pile)

Max Activating Token Index: 308

Text #4

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.5140. Min Act: -0.0000

Data Index: 1027686 (The Pile)

Max Activating Token Index: 1021

Text #5

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.4740. Min Act: -0.0000

Data Index: 260823 (The Pile)

Max Activating Token Index: 584

Text #6

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.5545. Min Act: -0.0000

Data Index: 1514935 (The Pile)

Max Activating Token Index: 237

Text #7

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.5623. Min Act: -0.0000

Data Index: 1881593 (The Pile)

Max Activating Token Index: 345

Text #8

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.4170. Min Act: -0.0000

Data Index: 1147003 (The Pile)

Max Activating Token Index: 662

Text #9

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.4842. Min Act: -0.0000

Data Index: 115432 (The Pile)

Max Activating Token Index: 567

Text #10

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.4803. Min Act: -0.0000

Data Index: 470360 (The Pile)

Max Activating Token Index: 47

Text #11

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.4423. Min Act: -0.0000

Data Index: 1922805 (The Pile)

Max Activating Token Index: 12

Text #12

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.5469. Min Act: -0.0000

Data Index: 721728 (The Pile)

Max Activating Token Index: 1005

Text #13

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.4501. Min Act: -0.0000

Data Index: 1018217 (The Pile)

Max Activating Token Index: 751

Text #14

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.4841. Min Act: -0.0000

Data Index: 716366 (The Pile)

Max Activating Token Index: 239

Text #15

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.4830. Min Act: -0.0000

Data Index: 1515369 (The Pile)

Max Activating Token Index: 489

Text #16

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.4341. Min Act: -0.0000

Data Index: 1094700 (The Pile)

Max Activating Token Index: 155

Text #17

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.4173. Min Act: -0.0000

Data Index: 908355 (The Pile)

Max Activating Token Index: 735

Text #18

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.5382. Min Act: -0.0000

Data Index: 1115194 (The Pile)

Max Activating Token Index: 264

Text #19

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.3619. Min Act: -0.0000

Data Index: 1646521 (The Pile)

Max Activating Token Index: 643