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

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

Neuron 3654 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.8450. Min Act: -0.0000

Data Index: 396382 (C4 (Web Text))

Max Activating Token Index: 898

Text #1

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.6891. Min Act: -0.0000

Data Index: 1019008 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.6615. Min Act: -0.0000

Data Index: 1270784 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.6539. Min Act: -0.0000

Data Index: 1098825 (C4 (Web Text))

Max Activating Token Index: 145

Text #4

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.5955. Min Act: -0.0000

Data Index: 891420 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.6027. Min Act: -0.0000

Data Index: 558009 (C4 (Web Text))

Max Activating Token Index: 361

Text #6

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.5721. Min Act: -0.0000

Data Index: 1135685 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.5542. Min Act: -0.0000

Data Index: 1119860 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.5632. Min Act: -0.0000

Data Index: 206229 (C4 (Web Text))

Max Activating Token Index: 418

Text #9

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.5735. Min Act: -0.0000

Data Index: 608608 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.5540. Min Act: -0.0000

Data Index: 485127 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.5323. Min Act: -0.0000

Data Index: 1302987 (C4 (Web Text))

Max Activating Token Index: 1010

Text #12

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.5305. Min Act: -0.0000

Data Index: 263959 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.5269. Min Act: -0.0000

Data Index: 370778 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.4858. Min Act: -0.0000

Data Index: 371152 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.5562. Min Act: -0.0000

Data Index: 240163 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.5584. Min Act: -0.0000

Data Index: 819196 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.5513. Min Act: -0.0000

Data Index: 15340 (C4 (Web Text))

Max Activating Token Index: 345

Text #18

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.5365. Min Act: -0.0000

Data Index: 404972 (C4 (Web Text))

Max Activating Token Index: 564

Text #19

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.5288. Min Act: -0.0000

Data Index: 582222 (C4 (Web Text))

Max Activating Token Index: 817