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

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

Neuron 833 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: 0.2947. Min Range: -0.2947

Max Act: 0.2947. Min Act: -0.0000

Data Index: 941129 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2735. Min Act: -0.0000

Data Index: 1252361 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2795. Min Act: -0.0000

Data Index: 5503 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2618. Min Act: -0.0000

Data Index: 487018 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2702. Min Act: -0.0000

Data Index: 387293 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2787. Min Act: -0.0000

Data Index: 723108 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2572. Min Act: -0.0000

Data Index: 284939 (C4 (Web Text))

Max Activating Token Index: 251

Text #7

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2633. Min Act: -0.0000

Data Index: 480882 (C4 (Web Text))

Max Activating Token Index: 824

Text #8

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2765. Min Act: -0.0000

Data Index: 124800 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2765. Min Act: -0.0000

Data Index: 191518 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2668. Min Act: -0.0000

Data Index: 1053677 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2623. Min Act: -0.0000

Data Index: 36701 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2485. Min Act: -0.0000

Data Index: 165691 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2749. Min Act: -0.0000

Data Index: 903829 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2530. Min Act: -0.0000

Data Index: 176416 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2418. Min Act: -0.0000

Data Index: 56348 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2484. Min Act: -0.0000

Data Index: 676341 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2579. Min Act: -0.0000

Data Index: 826129 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2548. Min Act: -0.0000

Data Index: 1085575 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2374. Min Act: -0.0000

Data Index: 362308 (C4 (Web Text))

Max Activating Token Index: 150