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

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

Neuron 4092 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.3226. Min Act: -0.0000

Data Index: 702536 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.3159. Min Act: -0.0000

Data Index: 887940 (C4 (Web Text))

Max Activating Token Index: 244

Text #2

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.3114. Min Act: -0.0000

Data Index: 1655277 (Python Code)

Max Activating Token Index: 211

Text #3

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2620. Min Act: -0.0000

Data Index: 800817 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.3062. Min Act: -0.0000

Data Index: 1460110 (Python Code)

Max Activating Token Index: 236

Text #5

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2816. Min Act: -0.0000

Data Index: 35897 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2934. Min Act: -0.0000

Data Index: 1583099 (Python Code)

Max Activating Token Index: 632

Text #7

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2512. Min Act: -0.0000

Data Index: 437345 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2505. Min Act: -0.0000

Data Index: 1525182 (Python Code)

Max Activating Token Index: 786

Text #9

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.3219. Min Act: -0.0000

Data Index: 1570255 (Python Code)

Max Activating Token Index: 243

Text #10

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2596. Min Act: -0.0000

Data Index: 1431621 (Python Code)

Max Activating Token Index: 703

Text #11

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2042. Min Act: -0.0000

Data Index: 526883 (C4 (Web Text))

Max Activating Token Index: 1016

Text #12

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2307. Min Act: -0.0000

Data Index: 1522797 (Python Code)

Max Activating Token Index: 404

Text #13

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2218. Min Act: -0.0000

Data Index: 1393164 (Python Code)

Max Activating Token Index: 653

Text #14

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2439. Min Act: -0.0000

Data Index: 1350233 (C4 (Web Text))

Max Activating Token Index: 257

Text #15

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2286. Min Act: -0.0000

Data Index: 271885 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2281. Min Act: -0.0000

Data Index: 1540192 (Python Code)

Max Activating Token Index: 649

Text #17

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2306. Min Act: -0.0000

Data Index: 843125 (C4 (Web Text))

Max Activating Token Index: 221

Text #18

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2129. Min Act: -0.0000

Data Index: 735620 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2126. Min Act: -0.0000

Data Index: 898051 (C4 (Web Text))

Max Activating Token Index: 184