Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 81 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2133. Min Act: -0.0003

Data Index: 904421 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2649. Min Act: -0.0003

Data Index: 272897 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2634. Min Act: -0.0003

Data Index: 494998 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2493. Min Act: -0.0003

Data Index: 808578 (C4 (Web Text))

Max Activating Token Index: 456

Text #4

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2461. Min Act: -0.0003

Data Index: 281349 (C4 (Web Text))

Max Activating Token Index: 303

Text #5

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2358. Min Act: -0.0003

Data Index: 693855 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2427. Min Act: -0.0003

Data Index: 733430 (C4 (Web Text))

Max Activating Token Index: 591

Text #7

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2053. Min Act: -0.0003

Data Index: 959355 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2077. Min Act: -0.0003

Data Index: 1327254 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2148. Min Act: -0.0003

Data Index: 37139 (C4 (Web Text))

Max Activating Token Index: 433

Text #10

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2222. Min Act: -0.0003

Data Index: 589132 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2013. Min Act: -0.0003

Data Index: 711738 (C4 (Web Text))

Max Activating Token Index: 643

Text #12

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2249. Min Act: -0.0003

Data Index: 1218 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.1949. Min Act: -0.0003

Data Index: 910630 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2143. Min Act: -0.0003

Data Index: 1055892 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.1844. Min Act: -0.0003

Data Index: 898201 (C4 (Web Text))

Max Activating Token Index: 835

Text #16

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2255. Min Act: -0.0003

Data Index: 576605 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.1968. Min Act: -0.0003

Data Index: 684479 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2053. Min Act: -0.0003

Data Index: 365734 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.1954. Min Act: -0.0003

Data Index: 765831 (C4 (Web Text))

Max Activating Token Index: 367