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

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

Neuron 4536 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1455. Min Range: -1.1455

Max Act: 1.1455. Min Act: -0.0001

Data Index: 529196 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 1.1455. Min Range: -1.1455

Max Act: 1.0442. Min Act: -0.0001

Data Index: 753996 (C4 (Web Text))

Max Activating Token Index: 531

Text #2

Max Range: 1.1455. Min Range: -1.1455

Max Act: 0.9706. Min Act: -0.0001

Data Index: 1277654 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 1.1455. Min Range: -1.1455

Max Act: 0.9655. Min Act: -0.0001

Data Index: 644206 (C4 (Web Text))

Max Activating Token Index: 417

Text #4

Max Range: 1.1455. Min Range: -1.1455

Max Act: 0.9360. Min Act: -0.0001

Data Index: 127334 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 1.1455. Min Range: -1.1455

Max Act: 0.8493. Min Act: -0.0001

Data Index: 568018 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 1.1455. Min Range: -1.1455

Max Act: 0.8142. Min Act: -0.0001

Data Index: 771668 (C4 (Web Text))

Max Activating Token Index: 819

Text #7

Max Range: 1.1455. Min Range: -1.1455

Max Act: 0.8530. Min Act: -0.0001

Data Index: 906461 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 1.1455. Min Range: -1.1455

Max Act: 0.8725. Min Act: -0.0001

Data Index: 96471 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 1.1455. Min Range: -1.1455

Max Act: 0.7723. Min Act: -0.0001

Data Index: 134739 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 1.1455. Min Range: -1.1455

Max Act: 0.8748. Min Act: -0.0001

Data Index: 307621 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 1.1455. Min Range: -1.1455

Max Act: 0.7986. Min Act: -0.0001

Data Index: 1089217 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 1.1455. Min Range: -1.1455

Max Act: 0.7837. Min Act: -0.0001

Data Index: 731611 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 1.1455. Min Range: -1.1455

Max Act: 0.7459. Min Act: -0.0001

Data Index: 309352 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 1.1455. Min Range: -1.1455

Max Act: 0.7968. Min Act: -0.0001

Data Index: 403694 (C4 (Web Text))

Max Activating Token Index: 484

Text #15

Max Range: 1.1455. Min Range: -1.1455

Max Act: 0.7914. Min Act: -0.0001

Data Index: 304118 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 1.1455. Min Range: -1.1455

Max Act: 0.7994. Min Act: -0.0001

Data Index: 1039583 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 1.1455. Min Range: -1.1455

Max Act: 0.7956. Min Act: -0.0001

Data Index: 731470 (C4 (Web Text))

Max Activating Token Index: 540

Text #18

Max Range: 1.1455. Min Range: -1.1455

Max Act: 0.7253. Min Act: -0.0001

Data Index: 934982 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 1.1455. Min Range: -1.1455

Max Act: 0.8031. Min Act: -0.0001

Data Index: 296684 (C4 (Web Text))

Max Activating Token Index: 103