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

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

Neuron 521 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.3133. Min Act: -0.0000

Data Index: 977840 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.3061. Min Act: -0.0000

Data Index: 290065 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2946. Min Act: -0.0001

Data Index: 557411 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2786. Min Act: -0.0000

Data Index: 376510 (C4 (Web Text))

Max Activating Token Index: 829

Text #4

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2966. Min Act: -0.0000

Data Index: 356202 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2852. Min Act: -0.0001

Data Index: 722344 (C4 (Web Text))

Max Activating Token Index: 465

Text #6

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2758. Min Act: -0.0000

Data Index: 1088014 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2664. Min Act: -0.0000

Data Index: 851445 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2577. Min Act: -0.0001

Data Index: 45698 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2666. Min Act: -0.0001

Data Index: 752476 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2531. Min Act: -0.0000

Data Index: 363854 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2594. Min Act: -0.0001

Data Index: 553562 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2472. Min Act: -0.0000

Data Index: 18061 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2529. Min Act: -0.0001

Data Index: 485996 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2536. Min Act: -0.0001

Data Index: 1008839 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2622. Min Act: -0.0001

Data Index: 25280 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2521. Min Act: -0.0001

Data Index: 1108205 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2407. Min Act: -0.0001

Data Index: 732406 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2472. Min Act: -0.0001

Data Index: 762239 (C4 (Web Text))

Max Activating Token Index: 370

Text #19

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2365. Min Act: -0.0000

Data Index: 439342 (C4 (Web Text))

Max Activating Token Index: 542