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

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

Neuron 4740 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.9086. Min Act: -0.0000

Data Index: 919184 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.6728. Min Act: -0.0000

Data Index: 580900 (C4 (Web Text))

Max Activating Token Index: 953

Text #2

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.6967. Min Act: -0.0000

Data Index: 353159 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.6212. Min Act: -0.0000

Data Index: 717187 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.6290. Min Act: -0.0000

Data Index: 330765 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.6480. Min Act: -0.0000

Data Index: 689920 (C4 (Web Text))

Max Activating Token Index: 634

Text #6

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.5689. Min Act: -0.0000

Data Index: 1309758 (C4 (Web Text))

Max Activating Token Index: 385

Text #7

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.5329. Min Act: -0.0000

Data Index: 1109644 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.5735. Min Act: -0.0000

Data Index: 346187 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.5432. Min Act: -0.0000

Data Index: 666487 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.5106. Min Act: -0.0000

Data Index: 435257 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.5439. Min Act: -0.0000

Data Index: 835708 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.5064. Min Act: -0.0000

Data Index: 252251 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.4876. Min Act: -0.0000

Data Index: 46758 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.4932. Min Act: -0.0000

Data Index: 705127 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.5096. Min Act: -0.0000

Data Index: 495778 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.4940. Min Act: -0.0000

Data Index: 516926 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.4193. Min Act: -0.0000

Data Index: 271246 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.4237. Min Act: -0.0000

Data Index: 1028524 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 0.9086. Min Range: -0.9086

Max Act: 0.4543. Min Act: -0.0000

Data Index: 1332014 (C4 (Web Text))

Max Activating Token Index: 93