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

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

Neuron 405 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: 0.7830. Min Range: -0.7830

Max Act: 0.7830. Min Act: -0.0000

Data Index: 888969 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.6161. Min Act: -0.0000

Data Index: 1349968 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.5220. Min Act: -0.0000

Data Index: 1157468 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.5178. Min Act: -0.0000

Data Index: 570421 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.5345. Min Act: -0.0000

Data Index: 629723 (C4 (Web Text))

Max Activating Token Index: 469

Text #5

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.5151. Min Act: -0.0000

Data Index: 1191914 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.4925. Min Act: -0.0000

Data Index: 288950 (C4 (Web Text))

Max Activating Token Index: 470

Text #7

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.4201. Min Act: -0.0000

Data Index: 405422 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.4047. Min Act: -0.0000

Data Index: 134925 (C4 (Web Text))

Max Activating Token Index: 170

Text #9

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.4237. Min Act: -0.0000

Data Index: 294232 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.3951. Min Act: -0.0000

Data Index: 1291962 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.4208. Min Act: -0.0000

Data Index: 1119231 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.3985. Min Act: -0.0000

Data Index: 1275237 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.3805. Min Act: -0.0000

Data Index: 38228 (C4 (Web Text))

Max Activating Token Index: 424

Text #14

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.4033. Min Act: -0.0000

Data Index: 96313 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.3745. Min Act: -0.0000

Data Index: 994750 (C4 (Web Text))

Max Activating Token Index: 965

Text #16

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.3693. Min Act: -0.0000

Data Index: 985939 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.3625. Min Act: -0.0000

Data Index: 139776 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.3761. Min Act: -0.0000

Data Index: 1120307 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.3689. Min Act: -0.0000

Data Index: 447344 (C4 (Web Text))

Max Activating Token Index: 947