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

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

Neuron 6124 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: 0.8113. Min Range: -0.8113

Max Act: 0.8113. Min Act: -0.0000

Data Index: 1208051 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.6131. Min Act: -0.0000

Data Index: 578683 (C4 (Web Text))

Max Activating Token Index: 440

Text #2

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.6086. Min Act: -0.0000

Data Index: 656380 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.6772. Min Act: -0.0000

Data Index: 1170945 (C4 (Web Text))

Max Activating Token Index: 983

Text #4

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.5450. Min Act: -0.0000

Data Index: 447039 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.5437. Min Act: -0.0000

Data Index: 935253 (C4 (Web Text))

Max Activating Token Index: 393

Text #6

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.5209. Min Act: -0.0000

Data Index: 732652 (C4 (Web Text))

Max Activating Token Index: 251

Text #7

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.6293. Min Act: -0.0000

Data Index: 1253670 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.5103. Min Act: -0.0000

Data Index: 107725 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.3997. Min Act: -0.0000

Data Index: 1329507 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.5044. Min Act: -0.0000

Data Index: 1086005 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.5138. Min Act: -0.0000

Data Index: 50307 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.4346. Min Act: -0.0000

Data Index: 1291881 (C4 (Web Text))

Max Activating Token Index: 570

Text #13

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.4518. Min Act: -0.0000

Data Index: 50079 (C4 (Web Text))

Max Activating Token Index: 489

Text #14

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.4343. Min Act: -0.0000

Data Index: 1098370 (C4 (Web Text))

Max Activating Token Index: 923

Text #15

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.4638. Min Act: -0.0000

Data Index: 871495 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.4298. Min Act: -0.0000

Data Index: 1194428 (C4 (Web Text))

Max Activating Token Index: 770

Text #17

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.4237. Min Act: -0.0000

Data Index: 21802 (C4 (Web Text))

Max Activating Token Index: 535

Text #18

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.4257. Min Act: -0.0000

Data Index: 478183 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.4771. Min Act: -0.0000

Data Index: 810600 (C4 (Web Text))

Max Activating Token Index: 482