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

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

Neuron 5817 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5039. Min Range: -0.5039

Max Act: 0.5039. Min Act: -0.0000

Data Index: 730339 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 0.5039. Min Range: -0.5039

Max Act: 0.3973. Min Act: 0.0000

Data Index: 1258657 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 0.5039. Min Range: -0.5039

Max Act: 0.3736. Min Act: -0.0000

Data Index: 354065 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 0.5039. Min Range: -0.5039

Max Act: 0.3575. Min Act: -0.0000

Data Index: 530835 (C4 (Web Text))

Max Activating Token Index: 251

Text #4

Max Range: 0.5039. Min Range: -0.5039

Max Act: 0.3542. Min Act: -0.0000

Data Index: 996738 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 0.5039. Min Range: -0.5039

Max Act: 0.3341. Min Act: -0.0000

Data Index: 1122535 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 0.5039. Min Range: -0.5039

Max Act: 0.3198. Min Act: -0.0000

Data Index: 1240617 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 0.5039. Min Range: -0.5039

Max Act: 0.3259. Min Act: -0.0000

Data Index: 10850 (C4 (Web Text))

Max Activating Token Index: 484

Text #8

Max Range: 0.5039. Min Range: -0.5039

Max Act: 0.3198. Min Act: -0.0000

Data Index: 824115 (C4 (Web Text))

Max Activating Token Index: 577

Text #9

Max Range: 0.5039. Min Range: -0.5039

Max Act: 0.3002. Min Act: -0.0000

Data Index: 1293474 (C4 (Web Text))

Max Activating Token Index: 409

Text #10

Max Range: 0.5039. Min Range: -0.5039

Max Act: 0.2947. Min Act: -0.0000

Data Index: 454808 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 0.5039. Min Range: -0.5039

Max Act: 0.2854. Min Act: 0.0001

Data Index: 1043571 (C4 (Web Text))

Max Activating Token Index: 678

Text #12

Max Range: 0.5039. Min Range: -0.5039

Max Act: 0.2912. Min Act: -0.0000

Data Index: 1263312 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 0.5039. Min Range: -0.5039

Max Act: 0.2907. Min Act: -0.0000

Data Index: 198662 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 0.5039. Min Range: -0.5039

Max Act: 0.2887. Min Act: -0.0000

Data Index: 191849 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 0.5039. Min Range: -0.5039

Max Act: 0.2939. Min Act: -0.0000

Data Index: 333200 (C4 (Web Text))

Max Activating Token Index: 422

Text #16

Max Range: 0.5039. Min Range: -0.5039

Max Act: 0.2857. Min Act: 0.0001

Data Index: 816546 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 0.5039. Min Range: -0.5039

Max Act: 0.2788. Min Act: -0.0000

Data Index: 914078 (C4 (Web Text))

Max Activating Token Index: 467

Text #18

Max Range: 0.5039. Min Range: -0.5039

Max Act: 0.2867. Min Act: -0.0000

Data Index: 371086 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 0.5039. Min Range: -0.5039

Max Act: 0.2766. Min Act: -0.0000

Data Index: 1283850 (C4 (Web Text))

Max Activating Token Index: 739