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

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

Neuron 332 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3834. Min Act: -0.0000

Data Index: 754957 (C4 (Web Text))

Max Activating Token Index: 408

Text #1

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3970. Min Act: -0.0000

Data Index: 1224558 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3757. Min Act: -0.0000

Data Index: 174562 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3597. Min Act: -0.0000

Data Index: 69248 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3226. Min Act: -0.0000

Data Index: 1019868 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3428. Min Act: -0.0000

Data Index: 1270019 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3331. Min Act: -0.0000

Data Index: 83947 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3336. Min Act: -0.0000

Data Index: 931640 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3340. Min Act: -0.0000

Data Index: 1350537 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3309. Min Act: -0.0001

Data Index: 1359340 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3304. Min Act: -0.0000

Data Index: 260 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3315. Min Act: -0.0000

Data Index: 210666 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3187. Min Act: -0.0000

Data Index: 705270 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3084. Min Act: -0.0000

Data Index: 1006765 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3163. Min Act: -0.0000

Data Index: 1009608 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3124. Min Act: -0.0000

Data Index: 1279034 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3220. Min Act: -0.0000

Data Index: 631838 (C4 (Web Text))

Max Activating Token Index: 497

Text #17

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2968. Min Act: -0.0000

Data Index: 885668 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3048. Min Act: -0.0000

Data Index: 13015 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3037. Min Act: -0.0000

Data Index: 1301051 (C4 (Web Text))

Max Activating Token Index: 923