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

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

Neuron 2647 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.4307. Min Act: -0.0000

Data Index: 605215 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.4209. Min Act: -0.0000

Data Index: 1004974 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.4103. Min Act: -0.0000

Data Index: 957563 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.3736. Min Act: 0.0000

Data Index: 1484205 (Python Code)

Max Activating Token Index: 201

Text #4

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.3808. Min Act: 0.0000

Data Index: 82960 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.3538. Min Act: 0.0000

Data Index: 1554913 (Python Code)

Max Activating Token Index: 294

Text #6

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.3411. Min Act: -0.0001

Data Index: 651429 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.3327. Min Act: -0.0000

Data Index: 363029 (C4 (Web Text))

Max Activating Token Index: 308

Text #8

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.3397. Min Act: -0.0000

Data Index: 698267 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.3422. Min Act: -0.0000

Data Index: 783558 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.3232. Min Act: -0.0000

Data Index: 34992 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.3221. Min Act: -0.0000

Data Index: 976239 (C4 (Web Text))

Max Activating Token Index: 426

Text #12

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.3222. Min Act: 0.0000

Data Index: 1468148 (Python Code)

Max Activating Token Index: 189

Text #13

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.3153. Min Act: -0.0001

Data Index: 1421389 (Python Code)

Max Activating Token Index: 1009

Text #14

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.3239. Min Act: -0.0000

Data Index: 1153376 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.3243. Min Act: -0.0000

Data Index: 664176 (C4 (Web Text))

Max Activating Token Index: 457

Text #16

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.3203. Min Act: -0.0000

Data Index: 1150889 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.3204. Min Act: -0.0001

Data Index: 1331539 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.3277. Min Act: 0.0000

Data Index: 730062 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.3056. Min Act: -0.0000

Data Index: 556637 (C4 (Web Text))

Max Activating Token Index: 920