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

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

Neuron 2591 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6343. Min Range: -4.6343

Max Act: 4.6343. Min Act: -0.0000

Data Index: 930646 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 4.6343. Min Range: -4.6343

Max Act: 4.4314. Min Act: -0.0000

Data Index: 1093852 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 4.6343. Min Range: -4.6343

Max Act: 4.1283. Min Act: -0.0000

Data Index: 1335903 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 4.6343. Min Range: -4.6343

Max Act: 4.3163. Min Act: -0.0000

Data Index: 604795 (C4 (Web Text))

Max Activating Token Index: 389

Text #4

Max Range: 4.6343. Min Range: -4.6343

Max Act: 3.8570. Min Act: -0.0000

Data Index: 132249 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 4.6343. Min Range: -4.6343

Max Act: 4.0072. Min Act: -0.0000

Data Index: 1007733 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 4.6343. Min Range: -4.6343

Max Act: 3.9913. Min Act: -0.0000

Data Index: 418402 (C4 (Web Text))

Max Activating Token Index: 493

Text #7

Max Range: 4.6343. Min Range: -4.6343

Max Act: 4.1270. Min Act: -0.0000

Data Index: 1007139 (C4 (Web Text))

Max Activating Token Index: 574

Text #8

Max Range: 4.6343. Min Range: -4.6343

Max Act: 3.7271. Min Act: -0.0000

Data Index: 1009864 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 4.6343. Min Range: -4.6343

Max Act: 3.8889. Min Act: -0.0000

Data Index: 191726 (C4 (Web Text))

Max Activating Token Index: 330

Text #10

Max Range: 4.6343. Min Range: -4.6343

Max Act: 4.0464. Min Act: -0.0000

Data Index: 411394 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 4.6343. Min Range: -4.6343

Max Act: 3.8689. Min Act: -0.0000

Data Index: 286736 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 4.6343. Min Range: -4.6343

Max Act: 3.8736. Min Act: -0.0000

Data Index: 986072 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 4.6343. Min Range: -4.6343

Max Act: 3.8482. Min Act: -0.0000

Data Index: 1191004 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 4.6343. Min Range: -4.6343

Max Act: 3.8182. Min Act: -0.0000

Data Index: 1260370 (C4 (Web Text))

Max Activating Token Index: 521

Text #15

Max Range: 4.6343. Min Range: -4.6343

Max Act: 3.6689. Min Act: -0.0000

Data Index: 1130915 (C4 (Web Text))

Max Activating Token Index: 525

Text #16

Max Range: 4.6343. Min Range: -4.6343

Max Act: 4.1584. Min Act: -0.0000

Data Index: 88227 (C4 (Web Text))

Max Activating Token Index: 788

Text #17

Max Range: 4.6343. Min Range: -4.6343

Max Act: 3.6739. Min Act: -0.0000

Data Index: 342825 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 4.6343. Min Range: -4.6343

Max Act: 3.8032. Min Act: -0.0000

Data Index: 1198752 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 4.6343. Min Range: -4.6343

Max Act: 3.9709. Min Act: -0.0000

Data Index: 1059608 (C4 (Web Text))

Max Activating Token Index: 353