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

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

Neuron 6142 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.5820. Min Act: -0.0000

Data Index: 1425 (C4 (Web Text))

Max Activating Token Index: 337

Text #1

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.5381. Min Act: -0.0000

Data Index: 693816 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.5351. Min Act: -0.0000

Data Index: 1076073 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.4875. Min Act: -0.0000

Data Index: 1071949 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.4755. Min Act: -0.0000

Data Index: 1323438 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.4602. Min Act: -0.0000

Data Index: 924937 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.4359. Min Act: -0.0000

Data Index: 497209 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.4422. Min Act: -0.0000

Data Index: 448927 (C4 (Web Text))

Max Activating Token Index: 955

Text #8

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.4212. Min Act: -0.0000

Data Index: 902856 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.4151. Min Act: -0.0000

Data Index: 433924 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.3997. Min Act: -0.0000

Data Index: 948494 (C4 (Web Text))

Max Activating Token Index: 476

Text #11

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.4377. Min Act: -0.0000

Data Index: 297566 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.4071. Min Act: -0.0000

Data Index: 1000528 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.4052. Min Act: -0.0000

Data Index: 587709 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.4088. Min Act: -0.0000

Data Index: 290839 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.4162. Min Act: -0.0000

Data Index: 1089583 (C4 (Web Text))

Max Activating Token Index: 712

Text #16

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.3959. Min Act: -0.0000

Data Index: 1143002 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.3925. Min Act: -0.0000

Data Index: 1027854 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.4073. Min Act: -0.0000

Data Index: 1155951 (C4 (Web Text))

Max Activating Token Index: 831

Text #19

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.3792. Min Act: -0.0000

Data Index: 930379 (C4 (Web Text))

Max Activating Token Index: 267