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

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

Neuron 1828 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.3893. Min Act: -0.0001

Data Index: 320236 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.4701. Min Act: -0.0001

Data Index: 730713 (C4 (Web Text))

Max Activating Token Index: 482

Text #2

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.2307. Min Act: -0.0001

Data Index: 314878 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.2634. Min Act: -0.0001

Data Index: 268422 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.1924. Min Act: -0.0001

Data Index: 1180818 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.2112. Min Act: -0.0001

Data Index: 221211 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.1131. Min Act: -0.0001

Data Index: 999831 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.2308. Min Act: -0.0001

Data Index: 712880 (C4 (Web Text))

Max Activating Token Index: 265

Text #8

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.0402. Min Act: -0.0001

Data Index: 292509 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.1179. Min Act: -0.0001

Data Index: 931619 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.0358. Min Act: -0.0001

Data Index: 1169009 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 1.4701. Min Range: -1.4701

Max Act: 0.9624. Min Act: -0.0001

Data Index: 136993 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 1.4701. Min Range: -1.4701

Max Act: 0.9136. Min Act: -0.0001

Data Index: 196259 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 1.4701. Min Range: -1.4701

Max Act: 0.9592. Min Act: -0.0001

Data Index: 944026 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.0136. Min Act: -0.0001

Data Index: 1339248 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 1.4701. Min Range: -1.4701

Max Act: 0.9749. Min Act: -0.0001

Data Index: 958910 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.0083. Min Act: -0.0001

Data Index: 733751 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 1.4701. Min Range: -1.4701

Max Act: 0.9929. Min Act: -0.0001

Data Index: 598273 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 1.4701. Min Range: -1.4701

Max Act: 0.9969. Min Act: -0.0001

Data Index: 844440 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 1.4701. Min Range: -1.4701

Max Act: 0.8810. Min Act: -0.0001

Data Index: 42471 (C4 (Web Text))

Max Activating Token Index: 939