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

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

Neuron 5519 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.7175. Min Act: -0.0001

Data Index: 1010384 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.7284. Min Act: -0.0001

Data Index: 902479 (C4 (Web Text))

Max Activating Token Index: 473

Text #2

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.7638. Min Act: -0.0001

Data Index: 1452297 (Python Code)

Max Activating Token Index: 705

Text #3

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.6513. Min Act: -0.0001

Data Index: 1128982 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.7134. Min Act: -0.0001

Data Index: 1298266 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.7158. Min Act: -0.0001

Data Index: 1356442 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.7363. Min Act: -0.0001

Data Index: 777691 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.6679. Min Act: -0.0001

Data Index: 440343 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.6170. Min Act: -0.0001

Data Index: 839065 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.7115. Min Act: -0.0001

Data Index: 666243 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.6288. Min Act: -0.0001

Data Index: 690323 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.6435. Min Act: -0.0001

Data Index: 837264 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.6345. Min Act: -0.0001

Data Index: 1142476 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.6121. Min Act: -0.0001

Data Index: 754138 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.5907. Min Act: -0.0001

Data Index: 1274466 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.5849. Min Act: -0.0001

Data Index: 358107 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.5990. Min Act: -0.0001

Data Index: 523982 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.6191. Min Act: -0.0001

Data Index: 450818 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.5671. Min Act: -0.0001

Data Index: 619810 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.5651. Min Act: -0.0001

Data Index: 1138140 (C4 (Web Text))

Max Activating Token Index: 832