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

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

Neuron 3588 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: 3.1637. Min Range: -3.1637

Max Act: 3.1637. Min Act: -0.0000

Data Index: 491479 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.6440. Min Act: -0.0000

Data Index: 260363 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.7575. Min Act: -0.0000

Data Index: 1079286 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.4808. Min Act: -0.0000

Data Index: 249856 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.6086. Min Act: -0.0000

Data Index: 9734 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.5946. Min Act: -0.0000

Data Index: 993430 (C4 (Web Text))

Max Activating Token Index: 412

Text #6

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.4570. Min Act: -0.0000

Data Index: 379548 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.3186. Min Act: -0.0000

Data Index: 1270553 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.2320. Min Act: -0.0000

Data Index: 858211 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.1221. Min Act: -0.0000

Data Index: 672208 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.3565. Min Act: -0.0000

Data Index: 999042 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.3469. Min Act: -0.0000

Data Index: 187472 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.1127. Min Act: -0.0000

Data Index: 522999 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.2695. Min Act: -0.0000

Data Index: 507919 (C4 (Web Text))

Max Activating Token Index: 534

Text #14

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.3462. Min Act: -0.0000

Data Index: 1268304 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.0942. Min Act: -0.0000

Data Index: 1355919 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.0769. Min Act: -0.0000

Data Index: 71390 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.0831. Min Act: -0.0000

Data Index: 55371 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.1809. Min Act: -0.0000

Data Index: 1192346 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.2791. Min Act: -0.0000

Data Index: 886042 (C4 (Web Text))

Max Activating Token Index: 548