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

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

Neuron 3116 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.3303. Min Act: -0.0000

Data Index: 688418 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2982. Min Act: -0.0001

Data Index: 364128 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2959. Min Act: -0.0000

Data Index: 168375 (C4 (Web Text))

Max Activating Token Index: 846

Text #3

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2863. Min Act: -0.0000

Data Index: 670921 (C4 (Web Text))

Max Activating Token Index: 453

Text #4

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2475. Min Act: -0.0000

Data Index: 220443 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2527. Min Act: -0.0001

Data Index: 624003 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2514. Min Act: -0.0000

Data Index: 397843 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2491. Min Act: -0.0000

Data Index: 777650 (C4 (Web Text))

Max Activating Token Index: 450

Text #8

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2407. Min Act: -0.0001

Data Index: 1164915 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2417. Min Act: -0.0001

Data Index: 1128482 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2453. Min Act: -0.0000

Data Index: 395193 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2354. Min Act: -0.0001

Data Index: 946715 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2353. Min Act: -0.0001

Data Index: 973392 (C4 (Web Text))

Max Activating Token Index: 629

Text #13

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2322. Min Act: -0.0000

Data Index: 33673 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2157. Min Act: -0.0000

Data Index: 1339105 (C4 (Web Text))

Max Activating Token Index: 469

Text #15

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2208. Min Act: -0.0000

Data Index: 506702 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.1942. Min Act: -0.0001

Data Index: 190058 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2161. Min Act: -0.0000

Data Index: 493477 (C4 (Web Text))

Max Activating Token Index: 903

Text #18

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2047. Min Act: -0.0001

Data Index: 152241 (C4 (Web Text))

Max Activating Token Index: 848

Text #19

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2053. Min Act: -0.0000

Data Index: 548436 (C4 (Web Text))

Max Activating Token Index: 435