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

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

Neuron 676 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.4575. Min Act: -0.0001

Data Index: 1100867 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.2764. Min Act: -0.0001

Data Index: 1287590 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.3018. Min Act: -0.0001

Data Index: 446490 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.2757. Min Act: -0.0001

Data Index: 1311162 (C4 (Web Text))

Max Activating Token Index: 295

Text #4

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.2686. Min Act: -0.0001

Data Index: 336520 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.2535. Min Act: -0.0001

Data Index: 1033343 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.2474. Min Act: -0.0001

Data Index: 637455 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.2531. Min Act: -0.0001

Data Index: 907565 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.2793. Min Act: -0.0001

Data Index: 1347496 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.2596. Min Act: -0.0001

Data Index: 661753 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.2375. Min Act: -0.0001

Data Index: 594190 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.2451. Min Act: -0.0001

Data Index: 209253 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.2368. Min Act: -0.0001

Data Index: 1224036 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.2399. Min Act: -0.0001

Data Index: 458567 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.2415. Min Act: -0.0001

Data Index: 376814 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.2433. Min Act: -0.0001

Data Index: 834343 (C4 (Web Text))

Max Activating Token Index: 619

Text #16

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.2178. Min Act: -0.0001

Data Index: 81827 (C4 (Web Text))

Max Activating Token Index: 790

Text #17

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.2223. Min Act: -0.0001

Data Index: 781136 (C4 (Web Text))

Max Activating Token Index: 99

Text #18

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.2084. Min Act: -0.0001

Data Index: 351950 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.2201. Min Act: -0.0001

Data Index: 244177 (C4 (Web Text))

Max Activating Token Index: 50