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

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

Neuron 1295 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 11.7173. Min Range: -11.7173

Max Act: 11.7173. Min Act: -0.0000

Data Index: 430416 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 11.7173. Min Range: -11.7173

Max Act: 10.6835. Min Act: -0.0000

Data Index: 59475 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 11.7173. Min Range: -11.7173

Max Act: 10.5291. Min Act: -0.0000

Data Index: 444275 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 11.7173. Min Range: -11.7173

Max Act: 10.8816. Min Act: -0.0000

Data Index: 284745 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 11.7173. Min Range: -11.7173

Max Act: 10.4991. Min Act: -0.0000

Data Index: 611879 (C4 (Web Text))

Max Activating Token Index: 343

Text #5

Max Range: 11.7173. Min Range: -11.7173

Max Act: 10.2562. Min Act: -0.0000

Data Index: 1112029 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 11.7173. Min Range: -11.7173

Max Act: 10.0477. Min Act: -0.0000

Data Index: 863413 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 11.7173. Min Range: -11.7173

Max Act: 10.2901. Min Act: -0.0000

Data Index: 1300286 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 11.7173. Min Range: -11.7173

Max Act: 10.2598. Min Act: -0.0000

Data Index: 290629 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 11.7173. Min Range: -11.7173

Max Act: 10.0341. Min Act: -0.0000

Data Index: 1168077 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 11.7173. Min Range: -11.7173

Max Act: 9.4461. Min Act: -0.0000

Data Index: 554859 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 11.7173. Min Range: -11.7173

Max Act: 9.8744. Min Act: -0.0000

Data Index: 304691 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 11.7173. Min Range: -11.7173

Max Act: 10.2464. Min Act: -0.0000

Data Index: 620862 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 11.7173. Min Range: -11.7173

Max Act: 9.6120. Min Act: -0.0000

Data Index: 751845 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 11.7173. Min Range: -11.7173

Max Act: 9.6168. Min Act: -0.0000

Data Index: 1112849 (C4 (Web Text))

Max Activating Token Index: 547

Text #15

Max Range: 11.7173. Min Range: -11.7173

Max Act: 9.8474. Min Act: -0.0000

Data Index: 64274 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 11.7173. Min Range: -11.7173

Max Act: 9.5705. Min Act: -0.0000

Data Index: 1312574 (C4 (Web Text))

Max Activating Token Index: 389

Text #17

Max Range: 11.7173. Min Range: -11.7173

Max Act: 9.5254. Min Act: -0.0000

Data Index: 471990 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 11.7173. Min Range: -11.7173

Max Act: 9.4992. Min Act: -0.0000

Data Index: 183452 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 11.7173. Min Range: -11.7173

Max Act: 9.6282. Min Act: -0.0000

Data Index: 343664 (C4 (Web Text))

Max Activating Token Index: 385