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

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

Neuron 836 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1386. Min Range: -1.1386

Max Act: 1.1386. Min Act: -0.0000

Data Index: 206159 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 1.1386. Min Range: -1.1386

Max Act: 1.1371. Min Act: -0.0000

Data Index: 30303 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 1.1386. Min Range: -1.1386

Max Act: 1.1349. Min Act: -0.0000

Data Index: 471606 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 1.1386. Min Range: -1.1386

Max Act: 1.0246. Min Act: -0.0000

Data Index: 1311176 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 1.1386. Min Range: -1.1386

Max Act: 1.0414. Min Act: -0.0000

Data Index: 441857 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 1.1386. Min Range: -1.1386

Max Act: 1.0621. Min Act: -0.0000

Data Index: 280768 (C4 (Web Text))

Max Activating Token Index: 456

Text #6

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.9979. Min Act: -0.0000

Data Index: 528587 (C4 (Web Text))

Max Activating Token Index: 244

Text #7

Max Range: 1.1386. Min Range: -1.1386

Max Act: 1.0012. Min Act: -0.0000

Data Index: 638383 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.9144. Min Act: -0.0000

Data Index: 100357 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.8633. Min Act: -0.0000

Data Index: 1207644 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.8847. Min Act: -0.0000

Data Index: 930538 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.9476. Min Act: -0.0000

Data Index: 477484 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.8697. Min Act: -0.0000

Data Index: 942953 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.9042. Min Act: -0.0000

Data Index: 1328127 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.8985. Min Act: -0.0000

Data Index: 73709 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.8956. Min Act: -0.0000

Data Index: 869654 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.8830. Min Act: -0.0000

Data Index: 364354 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.8696. Min Act: -0.0000

Data Index: 351853 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.8029. Min Act: -0.0000

Data Index: 778122 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 1.1386. Min Range: -1.1386

Max Act: 0.9795. Min Act: -0.0000

Data Index: 731787 (C4 (Web Text))

Max Activating Token Index: 353