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

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

Neuron 4492 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0787. Min Range: -1.0787

Max Act: 1.0787. Min Act: -0.0000

Data Index: 691433 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 1.0787. Min Range: -1.0787

Max Act: 1.0345. Min Act: -0.0000

Data Index: 529542 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 1.0787. Min Range: -1.0787

Max Act: 0.8456. Min Act: -0.0000

Data Index: 344316 (C4 (Web Text))

Max Activating Token Index: 787

Text #3

Max Range: 1.0787. Min Range: -1.0787

Max Act: 0.8875. Min Act: -0.0000

Data Index: 993084 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 1.0787. Min Range: -1.0787

Max Act: 0.8174. Min Act: -0.0000

Data Index: 531985 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 1.0787. Min Range: -1.0787

Max Act: 0.8123. Min Act: -0.0000

Data Index: 1525978 (Python Code)

Max Activating Token Index: 626

Text #6

Max Range: 1.0787. Min Range: -1.0787

Max Act: 0.7958. Min Act: -0.0000

Data Index: 908977 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 1.0787. Min Range: -1.0787

Max Act: 0.7680. Min Act: -0.0000

Data Index: 1207293 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 1.0787. Min Range: -1.0787

Max Act: 0.7608. Min Act: -0.0000

Data Index: 889801 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 1.0787. Min Range: -1.0787

Max Act: 0.7352. Min Act: -0.0000

Data Index: 703879 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 1.0787. Min Range: -1.0787

Max Act: 0.7486. Min Act: -0.0000

Data Index: 308399 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 1.0787. Min Range: -1.0787

Max Act: 0.7397. Min Act: -0.0000

Data Index: 1017539 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 1.0787. Min Range: -1.0787

Max Act: 0.7285. Min Act: -0.0000

Data Index: 389575 (C4 (Web Text))

Max Activating Token Index: 559

Text #13

Max Range: 1.0787. Min Range: -1.0787

Max Act: 0.7212. Min Act: -0.0000

Data Index: 1028521 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 1.0787. Min Range: -1.0787

Max Act: 0.6944. Min Act: -0.0000

Data Index: 1325602 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 1.0787. Min Range: -1.0787

Max Act: 0.7092. Min Act: -0.0000

Data Index: 1277135 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 1.0787. Min Range: -1.0787

Max Act: 0.7056. Min Act: -0.0000

Data Index: 386900 (C4 (Web Text))

Max Activating Token Index: 1021

Text #17

Max Range: 1.0787. Min Range: -1.0787

Max Act: 0.7020. Min Act: -0.0000

Data Index: 868560 (C4 (Web Text))

Max Activating Token Index: 759

Text #18

Max Range: 1.0787. Min Range: -1.0787

Max Act: 0.6857. Min Act: -0.0000

Data Index: 911109 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 1.0787. Min Range: -1.0787

Max Act: 0.6971. Min Act: -0.0000

Data Index: 531023 (C4 (Web Text))

Max Activating Token Index: 967