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

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

Neuron 2251 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: 2.1369. Min Range: -2.1369

Max Act: 2.1369. Min Act: -0.0000

Data Index: 570079 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 2.1369. Min Range: -2.1369

Max Act: 1.9597. Min Act: -0.0000

Data Index: 272231 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 2.1369. Min Range: -2.1369

Max Act: 1.7461. Min Act: -0.0000

Data Index: 750546 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 2.1369. Min Range: -2.1369

Max Act: 1.7539. Min Act: -0.0000

Data Index: 1128185 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 2.1369. Min Range: -2.1369

Max Act: 1.6650. Min Act: -0.0000

Data Index: 529014 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 2.1369. Min Range: -2.1369

Max Act: 1.7515. Min Act: -0.0000

Data Index: 1052510 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 2.1369. Min Range: -2.1369

Max Act: 1.6460. Min Act: -0.0000

Data Index: 669247 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 2.1369. Min Range: -2.1369

Max Act: 1.7084. Min Act: -0.0000

Data Index: 544914 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 2.1369. Min Range: -2.1369

Max Act: 1.6099. Min Act: -0.0000

Data Index: 401689 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 2.1369. Min Range: -2.1369

Max Act: 1.6885. Min Act: -0.0000

Data Index: 583652 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 2.1369. Min Range: -2.1369

Max Act: 1.5675. Min Act: -0.0000

Data Index: 106031 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 2.1369. Min Range: -2.1369

Max Act: 1.5439. Min Act: -0.0000

Data Index: 931384 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 2.1369. Min Range: -2.1369

Max Act: 1.6040. Min Act: -0.0000

Data Index: 816952 (C4 (Web Text))

Max Activating Token Index: 773

Text #13

Max Range: 2.1369. Min Range: -2.1369

Max Act: 1.6163. Min Act: -0.0000

Data Index: 1042721 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 2.1369. Min Range: -2.1369

Max Act: 1.6229. Min Act: -0.0000

Data Index: 1356705 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 2.1369. Min Range: -2.1369

Max Act: 1.5206. Min Act: -0.0000

Data Index: 774891 (C4 (Web Text))

Max Activating Token Index: 202

Text #16

Max Range: 2.1369. Min Range: -2.1369

Max Act: 1.5020. Min Act: -0.0000

Data Index: 1317093 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 2.1369. Min Range: -2.1369

Max Act: 1.5137. Min Act: -0.0000

Data Index: 182878 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 2.1369. Min Range: -2.1369

Max Act: 1.5964. Min Act: -0.0000

Data Index: 305264 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 2.1369. Min Range: -2.1369

Max Act: 1.5831. Min Act: -0.0000

Data Index: 553060 (C4 (Web Text))

Max Activating Token Index: 1021