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

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

Neuron 1618 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.7799. Min Range: -1.7799

Max Act: 1.7799. Min Act: -0.0002

Data Index: 499162 (C4 (Web Text))

Max Activating Token Index: 838

Text #1

Max Range: 1.7799. Min Range: -1.7799

Max Act: 1.6936. Min Act: -0.0002

Data Index: 380332 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 1.7799. Min Range: -1.7799

Max Act: 1.6854. Min Act: -0.0002

Data Index: 1004112 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 1.7799. Min Range: -1.7799

Max Act: 1.6175. Min Act: -0.0002

Data Index: 704510 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 1.7799. Min Range: -1.7799

Max Act: 1.5414. Min Act: -0.0002

Data Index: 424469 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 1.7799. Min Range: -1.7799

Max Act: 1.5178. Min Act: -0.0002

Data Index: 200211 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 1.7799. Min Range: -1.7799

Max Act: 1.4645. Min Act: -0.0002

Data Index: 99023 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 1.7799. Min Range: -1.7799

Max Act: 1.5269. Min Act: -0.0002

Data Index: 840477 (C4 (Web Text))

Max Activating Token Index: 40

Text #8

Max Range: 1.7799. Min Range: -1.7799

Max Act: 1.4550. Min Act: -0.0002

Data Index: 1076657 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 1.7799. Min Range: -1.7799

Max Act: 1.4364. Min Act: -0.0002

Data Index: 366247 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 1.7799. Min Range: -1.7799

Max Act: 1.4220. Min Act: -0.0002

Data Index: 954909 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 1.7799. Min Range: -1.7799

Max Act: 1.5106. Min Act: -0.0002

Data Index: 12641 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 1.7799. Min Range: -1.7799

Max Act: 1.4165. Min Act: -0.0002

Data Index: 933167 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 1.7799. Min Range: -1.7799

Max Act: 1.4025. Min Act: -0.0002

Data Index: 1099839 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 1.7799. Min Range: -1.7799

Max Act: 1.3965. Min Act: -0.0002

Data Index: 444423 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 1.7799. Min Range: -1.7799

Max Act: 1.4169. Min Act: -0.0002

Data Index: 1186667 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 1.7799. Min Range: -1.7799

Max Act: 1.4086. Min Act: -0.0002

Data Index: 37033 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 1.7799. Min Range: -1.7799

Max Act: 1.4309. Min Act: -0.0002

Data Index: 1087091 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 1.7799. Min Range: -1.7799

Max Act: 1.4247. Min Act: -0.0002

Data Index: 493472 (C4 (Web Text))

Max Activating Token Index: 857

Text #19

Max Range: 1.7799. Min Range: -1.7799

Max Act: 1.4206. Min Act: -0.0002

Data Index: 1141916 (C4 (Web Text))

Max Activating Token Index: 6