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

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

Neuron 2413 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.2168. Min Act: -0.0000

Data Index: 720997 (C4 (Web Text))

Max Activating Token Index: 366

Text #1

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.2137. Min Act: -0.0000

Data Index: 1283864 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1970. Min Act: -0.0000

Data Index: 484377 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1796. Min Act: -0.0000

Data Index: 945313 (C4 (Web Text))

Max Activating Token Index: 207

Text #4

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1532. Min Act: -0.0000

Data Index: 1116429 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1564. Min Act: -0.0000

Data Index: 551691 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1387. Min Act: -0.0000

Data Index: 159761 (C4 (Web Text))

Max Activating Token Index: 474

Text #7

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1380. Min Act: -0.0000

Data Index: 1337298 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1417. Min Act: -0.0000

Data Index: 935307 (C4 (Web Text))

Max Activating Token Index: 643

Text #9

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1250. Min Act: -0.0000

Data Index: 761687 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1293. Min Act: -0.0000

Data Index: 694157 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1169. Min Act: -0.0000

Data Index: 261412 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1142. Min Act: -0.0000

Data Index: 948569 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1118. Min Act: -0.0000

Data Index: 55374 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1093. Min Act: -0.0000

Data Index: 374467 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1043. Min Act: -0.0000

Data Index: 240031 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1084. Min Act: -0.0000

Data Index: 262642 (C4 (Web Text))

Max Activating Token Index: 894

Text #17

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.0993. Min Act: -0.0000

Data Index: 148006 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1127. Min Act: -0.0000

Data Index: 116056 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.0986. Min Act: -0.0000

Data Index: 162575 (C4 (Web Text))

Max Activating Token Index: 439