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

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

Neuron 1393 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: 1.9287. Min Range: -1.9287

Max Act: 1.8893. Min Act: -0.0000

Data Index: 925810 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 1.9287. Min Range: -1.9287

Max Act: 1.9287. Min Act: -0.0000

Data Index: 623170 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 1.9287. Min Range: -1.9287

Max Act: 1.7520. Min Act: -0.0000

Data Index: 989353 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 1.9287. Min Range: -1.9287

Max Act: 1.7627. Min Act: -0.0000

Data Index: 206065 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 1.9287. Min Range: -1.9287

Max Act: 1.8320. Min Act: -0.0000

Data Index: 15755 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 1.9287. Min Range: -1.9287

Max Act: 1.7320. Min Act: -0.0000

Data Index: 1203066 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 1.9287. Min Range: -1.9287

Max Act: 1.6419. Min Act: -0.0000

Data Index: 759486 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 1.9287. Min Range: -1.9287

Max Act: 1.4442. Min Act: -0.0000

Data Index: 86564 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 1.9287. Min Range: -1.9287

Max Act: 1.4628. Min Act: -0.0000

Data Index: 818564 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 1.9287. Min Range: -1.9287

Max Act: 1.4791. Min Act: -0.0000

Data Index: 569803 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 1.9287. Min Range: -1.9287

Max Act: 1.6860. Min Act: -0.0001

Data Index: 260923 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 1.9287. Min Range: -1.9287

Max Act: 1.6138. Min Act: -0.0001

Data Index: 724162 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 1.9287. Min Range: -1.9287

Max Act: 1.5328. Min Act: -0.0000

Data Index: 952195 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 1.9287. Min Range: -1.9287

Max Act: 1.5845. Min Act: -0.0000

Data Index: 1077768 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 1.9287. Min Range: -1.9287

Max Act: 1.5881. Min Act: -0.0000

Data Index: 246345 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 1.9287. Min Range: -1.9287

Max Act: 1.3288. Min Act: -0.0000

Data Index: 1332222 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 1.9287. Min Range: -1.9287

Max Act: 1.5540. Min Act: -0.0000

Data Index: 1202524 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 1.9287. Min Range: -1.9287

Max Act: 1.4615. Min Act: -0.0000

Data Index: 920108 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 1.9287. Min Range: -1.9287

Max Act: 1.4146. Min Act: -0.0000

Data Index: 859011 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 1.9287. Min Range: -1.9287

Max Act: 1.2729. Min Act: -0.0000

Data Index: 168528 (C4 (Web Text))

Max Activating Token Index: 713