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

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

Neuron 3148 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 12.1574. Min Range: -12.1574

Max Act: 12.1574. Min Act: -0.0001

Data Index: 897824 (C4 (Web Text))

Max Activating Token Index: 946

Text #1

Max Range: 12.1574. Min Range: -12.1574

Max Act: 11.9955. Min Act: -0.0001

Data Index: 861840 (C4 (Web Text))

Max Activating Token Index: 425

Text #2

Max Range: 12.1574. Min Range: -12.1574

Max Act: 9.9312. Min Act: -0.0000

Data Index: 307059 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 12.1574. Min Range: -12.1574

Max Act: 10.2461. Min Act: -0.0001

Data Index: 76384 (C4 (Web Text))

Max Activating Token Index: 354

Text #4

Max Range: 12.1574. Min Range: -12.1574

Max Act: 10.5232. Min Act: -0.0000

Data Index: 856862 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 12.1574. Min Range: -12.1574

Max Act: 8.4103. Min Act: -0.0000

Data Index: 997284 (C4 (Web Text))

Max Activating Token Index: 933

Text #6

Max Range: 12.1574. Min Range: -12.1574

Max Act: 9.1563. Min Act: -0.0001

Data Index: 1364295 (Python Code)

Max Activating Token Index: 931

Text #7

Max Range: 12.1574. Min Range: -12.1574

Max Act: 9.7397. Min Act: -0.0001

Data Index: 1335442 (C4 (Web Text))

Max Activating Token Index: 400

Text #8

Max Range: 12.1574. Min Range: -12.1574

Max Act: 8.6153. Min Act: -0.0001

Data Index: 332921 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 12.1574. Min Range: -12.1574

Max Act: 8.8118. Min Act: -0.0001

Data Index: 1555341 (Python Code)

Max Activating Token Index: 356

Text #10

Max Range: 12.1574. Min Range: -12.1574

Max Act: 7.4911. Min Act: -0.0000

Data Index: 1223304 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 12.1574. Min Range: -12.1574

Max Act: 8.3186. Min Act: -0.0001

Data Index: 496488 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 12.1574. Min Range: -12.1574

Max Act: 8.3217. Min Act: -0.0001

Data Index: 1428452 (Python Code)

Max Activating Token Index: 62

Text #13

Max Range: 12.1574. Min Range: -12.1574

Max Act: 7.9851. Min Act: -0.0001

Data Index: 439043 (C4 (Web Text))

Max Activating Token Index: 417

Text #14

Max Range: 12.1574. Min Range: -12.1574

Max Act: 8.2167. Min Act: -0.0001

Data Index: 521096 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 12.1574. Min Range: -12.1574

Max Act: 7.4830. Min Act: -0.0001

Data Index: 299899 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 12.1574. Min Range: -12.1574

Max Act: 6.9942. Min Act: -0.0001

Data Index: 1294004 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 12.1574. Min Range: -12.1574

Max Act: 6.8837. Min Act: -0.0001

Data Index: 345219 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 12.1574. Min Range: -12.1574

Max Act: 7.3708. Min Act: -0.0001

Data Index: 1201753 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 12.1574. Min Range: -12.1574

Max Act: 6.3029. Min Act: -0.0001

Data Index: 565267 (C4 (Web Text))

Max Activating Token Index: 782