Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3125 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.4884. Min Act: -0.0001

Data Index: 38448 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.0143. Min Act: -0.0001

Data Index: 376113 (C4 (Web Text))

Max Activating Token Index: 852

Text #2

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.9988. Min Act: -0.0001

Data Index: 1287503 (C4 (Web Text))

Max Activating Token Index: 442

Text #3

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.9011. Min Act: -0.0001

Data Index: 447318 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.9892. Min Act: -0.0001

Data Index: 196692 (C4 (Web Text))

Max Activating Token Index: 417

Text #5

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.8911. Min Act: -0.0001

Data Index: 1006283 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.8596. Min Act: -0.0001

Data Index: 541810 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.8526. Min Act: -0.0001

Data Index: 38651 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.9659. Min Act: -0.0001

Data Index: 1067964 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.8622. Min Act: -0.0001

Data Index: 420820 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.8656. Min Act: -0.0001

Data Index: 370422 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.9098. Min Act: -0.0001

Data Index: 323341 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.8366. Min Act: -0.0001

Data Index: 399621 (C4 (Web Text))

Max Activating Token Index: 491

Text #13

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.8710. Min Act: -0.0001

Data Index: 339627 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.8449. Min Act: -0.0001

Data Index: 552662 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.8978. Min Act: -0.0001

Data Index: 35882 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.8329. Min Act: -0.0001

Data Index: 186097 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.7868. Min Act: -0.0001

Data Index: 918210 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.8353. Min Act: -0.0001

Data Index: 219000 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.8542. Min Act: -0.0001

Data Index: 376418 (C4 (Web Text))

Max Activating Token Index: 197