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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4194 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7226. Min Range: -1.7226

Max Act: 1.7226. Min Act: -0.0000

Data Index: 1387902 (Python Code)

Max Activating Token Index: 847

Text #1

Max Range: 1.7226. Min Range: -1.7226

Max Act: 1.5312. Min Act: -0.0000

Data Index: 1585336 (Python Code)

Max Activating Token Index: 398

Text #2

Max Range: 1.7226. Min Range: -1.7226

Max Act: 1.4442. Min Act: -0.0000

Data Index: 1386753 (Python Code)

Max Activating Token Index: 111

Text #3

Max Range: 1.7226. Min Range: -1.7226

Max Act: 1.4499. Min Act: -0.0000

Data Index: 1478182 (Python Code)

Max Activating Token Index: 930

Text #4

Max Range: 1.7226. Min Range: -1.7226

Max Act: 1.4415. Min Act: -0.0000

Data Index: 303263 (C4 (Web Text))

Max Activating Token Index: 458

Text #5

Max Range: 1.7226. Min Range: -1.7226

Max Act: 1.3397. Min Act: -0.0000

Data Index: 1394053 (Python Code)

Max Activating Token Index: 267

Text #6

Max Range: 1.7226. Min Range: -1.7226

Max Act: 1.3020. Min Act: -0.0000

Data Index: 1439939 (Python Code)

Max Activating Token Index: 1019

Text #7

Max Range: 1.7226. Min Range: -1.7226

Max Act: 1.2506. Min Act: -0.0000

Data Index: 162312 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 1.7226. Min Range: -1.7226

Max Act: 1.1805. Min Act: -0.0000

Data Index: 668036 (C4 (Web Text))

Max Activating Token Index: 548

Text #9

Max Range: 1.7226. Min Range: -1.7226

Max Act: 1.1937. Min Act: -0.0000

Data Index: 1420916 (Python Code)

Max Activating Token Index: 312

Text #10

Max Range: 1.7226. Min Range: -1.7226

Max Act: 1.1698. Min Act: -0.0000

Data Index: 1319231 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 1.7226. Min Range: -1.7226

Max Act: 1.2006. Min Act: -0.0000

Data Index: 775413 (C4 (Web Text))

Max Activating Token Index: 979

Text #12

Max Range: 1.7226. Min Range: -1.7226

Max Act: 1.0898. Min Act: -0.0000

Data Index: 217149 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 1.7226. Min Range: -1.7226

Max Act: 1.1105. Min Act: -0.0000

Data Index: 1455131 (Python Code)

Max Activating Token Index: 173

Text #14

Max Range: 1.7226. Min Range: -1.7226

Max Act: 1.1022. Min Act: -0.0000

Data Index: 1584311 (Python Code)

Max Activating Token Index: 977

Text #15

Max Range: 1.7226. Min Range: -1.7226

Max Act: 1.1667. Min Act: -0.0000

Data Index: 1401248 (Python Code)

Max Activating Token Index: 105

Text #16

Max Range: 1.7226. Min Range: -1.7226

Max Act: 1.1483. Min Act: -0.0000

Data Index: 599076 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 1.7226. Min Range: -1.7226

Max Act: 1.0046. Min Act: -0.0000

Data Index: 1320485 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 1.7226. Min Range: -1.7226

Max Act: 1.1714. Min Act: -0.0000

Data Index: 355432 (C4 (Web Text))

Max Activating Token Index: 463

Text #19

Max Range: 1.7226. Min Range: -1.7226

Max Act: 1.0036. Min Act: -0.0000

Data Index: 1188639 (C4 (Web Text))

Max Activating Token Index: 59