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

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

Neuron 1433 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0345. Min Range: -2.0345

Max Act: 2.0345. Min Act: -0.0001

Data Index: 1415817 (Python Code)

Max Activating Token Index: 388

Text #1

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.7952. Min Act: -0.0000

Data Index: 1585516 (Python Code)

Max Activating Token Index: 164

Text #2

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.3435. Min Act: -0.0000

Data Index: 1435734 (Python Code)

Max Activating Token Index: 896

Text #3

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.3145. Min Act: -0.0000

Data Index: 1437916 (Python Code)

Max Activating Token Index: 88

Text #4

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.3488. Min Act: -0.0000

Data Index: 1407553 (Python Code)

Max Activating Token Index: 182

Text #5

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.2895. Min Act: -0.0000

Data Index: 1399078 (Python Code)

Max Activating Token Index: 57

Text #6

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.4599. Min Act: -0.0001

Data Index: 1551284 (Python Code)

Max Activating Token Index: 919

Text #7

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.2881. Min Act: -0.0001

Data Index: 1422066 (Python Code)

Max Activating Token Index: 630

Text #8

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.1565. Min Act: -0.0000

Data Index: 1530283 (Python Code)

Max Activating Token Index: 960

Text #9

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.2146. Min Act: -0.0001

Data Index: 1585931 (Python Code)

Max Activating Token Index: 216

Text #10

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.3446. Min Act: -0.0000

Data Index: 1371433 (Python Code)

Max Activating Token Index: 354

Text #11

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.3420. Min Act: -0.0001

Data Index: 1383328 (Python Code)

Max Activating Token Index: 912

Text #12

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.3969. Min Act: -0.0001

Data Index: 1655578 (Python Code)

Max Activating Token Index: 167

Text #13

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.3131. Min Act: -0.0000

Data Index: 1427009 (Python Code)

Max Activating Token Index: 471

Text #14

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.3163. Min Act: -0.0001

Data Index: 1572129 (Python Code)

Max Activating Token Index: 927

Text #15

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.2087. Min Act: -0.0000

Data Index: 1450809 (Python Code)

Max Activating Token Index: 506

Text #16

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.2635. Min Act: -0.0000

Data Index: 1456454 (Python Code)

Max Activating Token Index: 109

Text #17

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.1611. Min Act: -0.0001

Data Index: 1434197 (Python Code)

Max Activating Token Index: 642

Text #18

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.2404. Min Act: -0.0001

Data Index: 1522212 (Python Code)

Max Activating Token Index: 646

Text #19

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.2337. Min Act: -0.0000

Data Index: 1647004 (Python Code)

Max Activating Token Index: 326