Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6116 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9780. Min Range: -1.9780

Max Act: 1.9780. Min Act: -0.0000

Data Index: 154116 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 1.9780. Min Range: -1.9780

Max Act: 1.2384. Min Act: -0.0000

Data Index: 1292374 (C4 (Web Text))

Max Activating Token Index: 663

Text #2

Max Range: 1.9780. Min Range: -1.9780

Max Act: 1.0994. Min Act: -0.0000

Data Index: 968020 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 1.9780. Min Range: -1.9780

Max Act: 1.2015. Min Act: -0.0000

Data Index: 958609 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 1.9780. Min Range: -1.9780

Max Act: 1.1198. Min Act: -0.0000

Data Index: 819056 (C4 (Web Text))

Max Activating Token Index: 293

Text #5

Max Range: 1.9780. Min Range: -1.9780

Max Act: 1.0313. Min Act: -0.0000

Data Index: 1000842 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 1.9780. Min Range: -1.9780

Max Act: 1.0244. Min Act: -0.0000

Data Index: 679837 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 1.9780. Min Range: -1.9780

Max Act: 1.0148. Min Act: -0.0000

Data Index: 293178 (C4 (Web Text))

Max Activating Token Index: 565

Text #8

Max Range: 1.9780. Min Range: -1.9780

Max Act: 1.0101. Min Act: -0.0000

Data Index: 451603 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 1.9780. Min Range: -1.9780

Max Act: 1.0020. Min Act: -0.0000

Data Index: 412933 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 1.9780. Min Range: -1.9780

Max Act: 0.9935. Min Act: -0.0000

Data Index: 81916 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 1.9780. Min Range: -1.9780

Max Act: 0.9826. Min Act: -0.0000

Data Index: 22497 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 1.9780. Min Range: -1.9780

Max Act: 0.9857. Min Act: -0.0000

Data Index: 1325317 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 1.9780. Min Range: -1.9780

Max Act: 0.8993. Min Act: -0.0000

Data Index: 1134680 (C4 (Web Text))

Max Activating Token Index: 573

Text #14

Max Range: 1.9780. Min Range: -1.9780

Max Act: 0.9451. Min Act: -0.0000

Data Index: 669639 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 1.9780. Min Range: -1.9780

Max Act: 0.8999. Min Act: -0.0000

Data Index: 192602 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 1.9780. Min Range: -1.9780

Max Act: 0.9582. Min Act: -0.0000

Data Index: 184388 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 1.9780. Min Range: -1.9780

Max Act: 0.8507. Min Act: -0.0000

Data Index: 808044 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 1.9780. Min Range: -1.9780

Max Act: 0.9087. Min Act: -0.0000

Data Index: 371409 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 1.9780. Min Range: -1.9780

Max Act: 0.8371. Min Act: -0.0000

Data Index: 377805 (C4 (Web Text))

Max Activating Token Index: 68