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

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

Neuron 4481 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0455. Min Range: -3.0455

Max Act: 3.0455. Min Act: -0.0000

Data Index: 117058 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 3.0455. Min Range: -3.0455

Max Act: 2.9858. Min Act: -0.0000

Data Index: 886538 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 3.0455. Min Range: -3.0455

Max Act: 2.7832. Min Act: -0.0000

Data Index: 1034989 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 3.0455. Min Range: -3.0455

Max Act: 2.9091. Min Act: -0.0000

Data Index: 427 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 3.0455. Min Range: -3.0455

Max Act: 2.7190. Min Act: -0.0000

Data Index: 1002245 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 3.0455. Min Range: -3.0455

Max Act: 2.6754. Min Act: -0.0000

Data Index: 985388 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 3.0455. Min Range: -3.0455

Max Act: 2.6700. Min Act: -0.0000

Data Index: 221749 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 3.0455. Min Range: -3.0455

Max Act: 2.5396. Min Act: -0.0000

Data Index: 232006 (C4 (Web Text))

Max Activating Token Index: 443

Text #8

Max Range: 3.0455. Min Range: -3.0455

Max Act: 2.3063. Min Act: -0.0000

Data Index: 803637 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 3.0455. Min Range: -3.0455

Max Act: 2.3585. Min Act: -0.0000

Data Index: 1153696 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 3.0455. Min Range: -3.0455

Max Act: 2.2618. Min Act: -0.0000

Data Index: 600164 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 3.0455. Min Range: -3.0455

Max Act: 2.2293. Min Act: -0.0000

Data Index: 1028696 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 3.0455. Min Range: -3.0455

Max Act: 2.3217. Min Act: -0.0000

Data Index: 1353394 (C4 (Web Text))

Max Activating Token Index: 577

Text #13

Max Range: 3.0455. Min Range: -3.0455

Max Act: 2.3070. Min Act: -0.0000

Data Index: 639832 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 3.0455. Min Range: -3.0455

Max Act: 2.1443. Min Act: -0.0000

Data Index: 312706 (C4 (Web Text))

Max Activating Token Index: 328

Text #15

Max Range: 3.0455. Min Range: -3.0455

Max Act: 2.2062. Min Act: -0.0000

Data Index: 537688 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 3.0455. Min Range: -3.0455

Max Act: 2.1812. Min Act: -0.0000

Data Index: 1135803 (C4 (Web Text))

Max Activating Token Index: 485

Text #17

Max Range: 3.0455. Min Range: -3.0455

Max Act: 2.0497. Min Act: -0.0000

Data Index: 362991 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 3.0455. Min Range: -3.0455

Max Act: 2.1420. Min Act: -0.0000

Data Index: 696742 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 3.0455. Min Range: -3.0455

Max Act: 2.1209. Min Act: -0.0000

Data Index: 895112 (C4 (Web Text))

Max Activating Token Index: 796