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

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

Neuron 786 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1978. Min Act: -0.0001

Data Index: 1222536 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1473. Min Act: -0.0001

Data Index: 1038277 (C4 (Web Text))

Max Activating Token Index: 591

Text #2

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1512. Min Act: -0.0001

Data Index: 275044 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1510. Min Act: -0.0001

Data Index: 58583 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1393. Min Act: -0.0001

Data Index: 418778 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1461. Min Act: -0.0001

Data Index: 1169398 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1348. Min Act: -0.0001

Data Index: 1058445 (C4 (Web Text))

Max Activating Token Index: 526

Text #7

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1288. Min Act: -0.0001

Data Index: 76314 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1261. Min Act: -0.0001

Data Index: 590348 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1203. Min Act: -0.0001

Data Index: 875518 (C4 (Web Text))

Max Activating Token Index: 434

Text #10

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1203. Min Act: -0.0001

Data Index: 122334 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1094. Min Act: -0.0001

Data Index: 1077895 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1160. Min Act: -0.0001

Data Index: 824010 (C4 (Web Text))

Max Activating Token Index: 579

Text #13

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1159. Min Act: -0.0001

Data Index: 682733 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1155. Min Act: -0.0001

Data Index: 149991 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1175. Min Act: -0.0001

Data Index: 529330 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1120. Min Act: -0.0001

Data Index: 1255485 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1119. Min Act: -0.0001

Data Index: 1287034 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1099. Min Act: -0.0001

Data Index: 1238890 (C4 (Web Text))

Max Activating Token Index: 945

Text #19

Max Range: 0.1978. Min Range: -0.1978

Max Act: 0.1042. Min Act: -0.0001

Data Index: 416625 (C4 (Web Text))

Max Activating Token Index: 399