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

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

Neuron 3327 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.4476. Min Act: 0.0000

Data Index: 899170 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3269. Min Act: -0.0000

Data Index: 1225271 (C4 (Web Text))

Max Activating Token Index: 400

Text #2

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3163. Min Act: -0.0000

Data Index: 601050 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3276. Min Act: -0.0000

Data Index: 905141 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3044. Min Act: 0.0000

Data Index: 1062381 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.2892. Min Act: -0.0000

Data Index: 300001 (C4 (Web Text))

Max Activating Token Index: 634

Text #6

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.2866. Min Act: 0.0000

Data Index: 695354 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.2872. Min Act: -0.0000

Data Index: 1183822 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.2639. Min Act: -0.0000

Data Index: 669037 (C4 (Web Text))

Max Activating Token Index: 966

Text #9

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.2711. Min Act: -0.0000

Data Index: 86048 (C4 (Web Text))

Max Activating Token Index: 484

Text #10

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.2579. Min Act: -0.0000

Data Index: 618558 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.2476. Min Act: -0.0000

Data Index: 654697 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.2608. Min Act: -0.0000

Data Index: 733401 (C4 (Web Text))

Max Activating Token Index: 589

Text #13

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.2567. Min Act: -0.0000

Data Index: 383898 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.2552. Min Act: -0.0000

Data Index: 392961 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.2449. Min Act: 0.0000

Data Index: 654246 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.2607. Min Act: -0.0000

Data Index: 408920 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.2594. Min Act: -0.0000

Data Index: 178166 (C4 (Web Text))

Max Activating Token Index: 856

Text #18

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.2570. Min Act: -0.0000

Data Index: 1265137 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.2327. Min Act: -0.0000

Data Index: 500364 (C4 (Web Text))

Max Activating Token Index: 350