Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1611 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1514. Min Range: -1.1514

Max Act: 1.1514. Min Act: -0.0001

Data Index: 2745 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 1.1514. Min Range: -1.1514

Max Act: 1.0943. Min Act: -0.0001

Data Index: 167713 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 1.1514. Min Range: -1.1514

Max Act: 1.0157. Min Act: -0.0001

Data Index: 318235 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 1.1514. Min Range: -1.1514

Max Act: 1.0699. Min Act: -0.0001

Data Index: 578590 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 1.1514. Min Range: -1.1514

Max Act: 1.0335. Min Act: -0.0001

Data Index: 60602 (C4 (Web Text))

Max Activating Token Index: 668

Text #5

Max Range: 1.1514. Min Range: -1.1514

Max Act: 1.0036. Min Act: -0.0001

Data Index: 1304392 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 1.1514. Min Range: -1.1514

Max Act: 1.0247. Min Act: -0.0001

Data Index: 285434 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 1.1514. Min Range: -1.1514

Max Act: 1.0251. Min Act: -0.0001

Data Index: 944082 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 1.1514. Min Range: -1.1514

Max Act: 1.0407. Min Act: -0.0000

Data Index: 250333 (C4 (Web Text))

Max Activating Token Index: 959

Text #9

Max Range: 1.1514. Min Range: -1.1514

Max Act: 1.0003. Min Act: -0.0001

Data Index: 1270748 (C4 (Web Text))

Max Activating Token Index: 136

Text #10

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.9573. Min Act: -0.0001

Data Index: 517368 (C4 (Web Text))

Max Activating Token Index: 925

Text #11

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.9599. Min Act: -0.0000

Data Index: 271961 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.9300. Min Act: -0.0001

Data Index: 736229 (C4 (Web Text))

Max Activating Token Index: 675

Text #13

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.9265. Min Act: -0.0001

Data Index: 258172 (C4 (Web Text))

Max Activating Token Index: 547

Text #14

Max Range: 1.1514. Min Range: -1.1514

Max Act: 1.0407. Min Act: -0.0001

Data Index: 661070 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.9429. Min Act: -0.0001

Data Index: 1086389 (C4 (Web Text))

Max Activating Token Index: 488

Text #16

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.9692. Min Act: -0.0001

Data Index: 90812 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.9110. Min Act: -0.0001

Data Index: 1338725 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.9095. Min Act: -0.0001

Data Index: 1232263 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.9120. Min Act: -0.0001

Data Index: 1159441 (C4 (Web Text))

Max Activating Token Index: 893