Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4460 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6967. Min Range: -1.6967

Max Act: 1.6967. Min Act: -0.0001

Data Index: 149063 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 1.6967. Min Range: -1.6967

Max Act: 1.6726. Min Act: -0.0001

Data Index: 129158 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 1.6967. Min Range: -1.6967

Max Act: 1.6203. Min Act: -0.0001

Data Index: 210907 (C4 (Web Text))

Max Activating Token Index: 160

Text #3

Max Range: 1.6967. Min Range: -1.6967

Max Act: 1.5906. Min Act: -0.0001

Data Index: 193937 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 1.6967. Min Range: -1.6967

Max Act: 1.4614. Min Act: -0.0001

Data Index: 236802 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 1.6967. Min Range: -1.6967

Max Act: 1.4445. Min Act: -0.0001

Data Index: 325382 (C4 (Web Text))

Max Activating Token Index: 204

Text #6

Max Range: 1.6967. Min Range: -1.6967

Max Act: 1.3884. Min Act: -0.0001

Data Index: 149325 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 1.6967. Min Range: -1.6967

Max Act: 1.4033. Min Act: -0.0001

Data Index: 272707 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 1.6967. Min Range: -1.6967

Max Act: 1.4383. Min Act: -0.0001

Data Index: 156819 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 1.6967. Min Range: -1.6967

Max Act: 1.6405. Min Act: -0.0001

Data Index: 23598 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 1.6967. Min Range: -1.6967

Max Act: 1.4233. Min Act: -0.0001

Data Index: 70875 (C4 (Web Text))

Max Activating Token Index: 914

Text #11

Max Range: 1.6967. Min Range: -1.6967

Max Act: 1.2991. Min Act: -0.0001

Data Index: 205246 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 1.6967. Min Range: -1.6967

Max Act: 1.3546. Min Act: -0.0001

Data Index: 989467 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 1.6967. Min Range: -1.6967

Max Act: 1.4600. Min Act: -0.0001

Data Index: 621326 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 1.6967. Min Range: -1.6967

Max Act: 1.3896. Min Act: -0.0001

Data Index: 884309 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 1.6967. Min Range: -1.6967

Max Act: 1.2421. Min Act: -0.0001

Data Index: 1181080 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 1.6967. Min Range: -1.6967

Max Act: 1.4114. Min Act: -0.0001

Data Index: 795877 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 1.6967. Min Range: -1.6967

Max Act: 1.4437. Min Act: -0.0001

Data Index: 428874 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 1.6967. Min Range: -1.6967

Max Act: 1.2678. Min Act: -0.0001

Data Index: 1319268 (C4 (Web Text))

Max Activating Token Index: 742

Text #19

Max Range: 1.6967. Min Range: -1.6967

Max Act: 1.4179. Min Act: -0.0001

Data Index: 1299808 (C4 (Web Text))

Max Activating Token Index: 74