Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2801 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8295. Min Range: -1.8295

Max Act: 1.8134. Min Act: -0.0000

Data Index: 955436 (C4 (Web Text))

Max Activating Token Index: 429

Text #1

Max Range: 1.8295. Min Range: -1.8295

Max Act: 1.7503. Min Act: -0.0000

Data Index: 644818 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 1.8295. Min Range: -1.8295

Max Act: 1.8295. Min Act: -0.0000

Data Index: 926227 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 1.8295. Min Range: -1.8295

Max Act: 1.7965. Min Act: -0.0000

Data Index: 534853 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 1.8295. Min Range: -1.8295

Max Act: 1.6796. Min Act: -0.0000

Data Index: 800565 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 1.8295. Min Range: -1.8295

Max Act: 1.7190. Min Act: -0.0000

Data Index: 324978 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 1.8295. Min Range: -1.8295

Max Act: 1.6054. Min Act: -0.0000

Data Index: 7372 (C4 (Web Text))

Max Activating Token Index: 95

Text #7

Max Range: 1.8295. Min Range: -1.8295

Max Act: 1.6255. Min Act: -0.0000

Data Index: 321069 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 1.8295. Min Range: -1.8295

Max Act: 1.4569. Min Act: -0.0000

Data Index: 204368 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 1.8295. Min Range: -1.8295

Max Act: 1.5442. Min Act: -0.0000

Data Index: 1008146 (C4 (Web Text))

Max Activating Token Index: 992

Text #10

Max Range: 1.8295. Min Range: -1.8295

Max Act: 1.5238. Min Act: -0.0000

Data Index: 1254272 (C4 (Web Text))

Max Activating Token Index: 338

Text #11

Max Range: 1.8295. Min Range: -1.8295

Max Act: 1.5415. Min Act: -0.0000

Data Index: 769004 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 1.8295. Min Range: -1.8295

Max Act: 1.3256. Min Act: -0.0000

Data Index: 432356 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 1.8295. Min Range: -1.8295

Max Act: 1.3762. Min Act: -0.0000

Data Index: 926613 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 1.8295. Min Range: -1.8295

Max Act: 1.3069. Min Act: -0.0000

Data Index: 1019983 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 1.8295. Min Range: -1.8295

Max Act: 1.2720. Min Act: -0.0000

Data Index: 104991 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 1.8295. Min Range: -1.8295

Max Act: 1.2601. Min Act: -0.0000

Data Index: 1404996 (Python Code)

Max Activating Token Index: 77

Text #17

Max Range: 1.8295. Min Range: -1.8295

Max Act: 1.2191. Min Act: -0.0000

Data Index: 226830 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 1.8295. Min Range: -1.8295

Max Act: 1.2599. Min Act: -0.0000

Data Index: 1620098 (Python Code)

Max Activating Token Index: 98

Text #19

Max Range: 1.8295. Min Range: -1.8295

Max Act: 0.9836. Min Act: -0.0000

Data Index: 741588 (C4 (Web Text))

Max Activating Token Index: 440