Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1447 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.3638. Min Act: -0.0001

Data Index: 1054869 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.3283. Min Act: -0.0001

Data Index: 1281981 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.3666. Min Act: -0.0001

Data Index: 322749 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.3461. Min Act: -0.0001

Data Index: 292104 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.3184. Min Act: -0.0001

Data Index: 725993 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.3271. Min Act: -0.0001

Data Index: 1230692 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.3428. Min Act: -0.0001

Data Index: 1211034 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.3236. Min Act: -0.0001

Data Index: 560444 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.3303. Min Act: -0.0001

Data Index: 1016331 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.3428. Min Act: -0.0001

Data Index: 314775 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.3220. Min Act: -0.0001

Data Index: 701086 (C4 (Web Text))

Max Activating Token Index: 492

Text #11

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.3085. Min Act: -0.0001

Data Index: 797911 (C4 (Web Text))

Max Activating Token Index: 682

Text #12

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.3275. Min Act: -0.0001

Data Index: 258422 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.3131. Min Act: -0.0001

Data Index: 1130960 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.3448. Min Act: -0.0001

Data Index: 876651 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.2972. Min Act: -0.0001

Data Index: 787561 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.3034. Min Act: -0.0001

Data Index: 1150513 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.3075. Min Act: -0.0001

Data Index: 128476 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.3194. Min Act: -0.0001

Data Index: 876193 (C4 (Web Text))

Max Activating Token Index: 961

Text #19

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.3219. Min Act: -0.0001

Data Index: 57444 (C4 (Web Text))

Max Activating Token Index: 771