Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1498 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.4983. Min Act: -0.0001

Data Index: 1318292 (C4 (Web Text))

Max Activating Token Index: 1010

Text #1

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.3333. Min Act: -0.0001

Data Index: 1076766 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.3588. Min Act: -0.0001

Data Index: 977686 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.2854. Min Act: -0.0001

Data Index: 975047 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.2613. Min Act: -0.0001

Data Index: 1273379 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.4128. Min Act: -0.0001

Data Index: 698617 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.3483. Min Act: -0.0001

Data Index: 589587 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.2835. Min Act: -0.0001

Data Index: 266913 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.3926. Min Act: -0.0001

Data Index: 575360 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.2461. Min Act: -0.0001

Data Index: 762601 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.2154. Min Act: -0.0001

Data Index: 689032 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.2127. Min Act: -0.0001

Data Index: 508801 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.2862. Min Act: -0.0001

Data Index: 662709 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.2549. Min Act: -0.0001

Data Index: 151172 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.2160. Min Act: -0.0001

Data Index: 762674 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.2355. Min Act: -0.0001

Data Index: 1200340 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.2097. Min Act: -0.0001

Data Index: 886611 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.2656. Min Act: -0.0001

Data Index: 608759 (C4 (Web Text))

Max Activating Token Index: 586

Text #18

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.2336. Min Act: -0.0001

Data Index: 1022601 (C4 (Web Text))

Max Activating Token Index: 512

Text #19

Max Range: 1.4983. Min Range: -1.4983

Max Act: 1.1142. Min Act: -0.0001

Data Index: 791348 (C4 (Web Text))

Max Activating Token Index: 169