Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2423 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.3173. Min Range: -6.3173

Max Act: 6.3173. Min Act: -0.0000

Data Index: 538382 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 6.3173. Min Range: -6.3173

Max Act: 5.5890. Min Act: -0.0000

Data Index: 160299 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 6.3173. Min Range: -6.3173

Max Act: 5.3030. Min Act: -0.0000

Data Index: 724642 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 6.3173. Min Range: -6.3173

Max Act: 4.9975. Min Act: -0.0000

Data Index: 1148085 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 6.3173. Min Range: -6.3173

Max Act: 4.7357. Min Act: -0.0000

Data Index: 777845 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 6.3173. Min Range: -6.3173

Max Act: 4.8965. Min Act: -0.0000

Data Index: 284111 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 6.3173. Min Range: -6.3173

Max Act: 4.4764. Min Act: -0.0000

Data Index: 519541 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 6.3173. Min Range: -6.3173

Max Act: 4.3057. Min Act: -0.0000

Data Index: 1303256 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 6.3173. Min Range: -6.3173

Max Act: 4.2698. Min Act: -0.0000

Data Index: 515854 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 6.3173. Min Range: -6.3173

Max Act: 4.2381. Min Act: -0.0000

Data Index: 505177 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 6.3173. Min Range: -6.3173

Max Act: 4.2145. Min Act: -0.0000

Data Index: 348021 (C4 (Web Text))

Max Activating Token Index: 666

Text #11

Max Range: 6.3173. Min Range: -6.3173

Max Act: 4.2003. Min Act: -0.0000

Data Index: 1278853 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 6.3173. Min Range: -6.3173

Max Act: 4.3887. Min Act: -0.0000

Data Index: 59068 (C4 (Web Text))

Max Activating Token Index: 556

Text #13

Max Range: 6.3173. Min Range: -6.3173

Max Act: 4.2712. Min Act: -0.0000

Data Index: 1252986 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 6.3173. Min Range: -6.3173

Max Act: 4.0932. Min Act: -0.0000

Data Index: 731217 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 6.3173. Min Range: -6.3173

Max Act: 3.9833. Min Act: -0.0000

Data Index: 150920 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 6.3173. Min Range: -6.3173

Max Act: 3.8244. Min Act: -0.0000

Data Index: 1133700 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 6.3173. Min Range: -6.3173

Max Act: 3.9708. Min Act: -0.0000

Data Index: 474053 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 6.3173. Min Range: -6.3173

Max Act: 3.8066. Min Act: -0.0000

Data Index: 777257 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 6.3173. Min Range: -6.3173

Max Act: 4.2993. Min Act: -0.0000

Data Index: 119778 (C4 (Web Text))

Max Activating Token Index: 864