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

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

Neuron 79 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0456. Min Act: -0.0001

Data Index: 481710 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0432. Min Act: -0.0001

Data Index: 1284367 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0455. Min Act: -0.0001

Data Index: 1047928 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0414. Min Act: -0.0001

Data Index: 871077 (C4 (Web Text))

Max Activating Token Index: 404

Text #4

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0308. Min Act: -0.0002

Data Index: 477733 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0312. Min Act: -0.0001

Data Index: 1122774 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0307. Min Act: -0.0001

Data Index: 1254902 (C4 (Web Text))

Max Activating Token Index: 247

Text #7

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0293. Min Act: -0.0001

Data Index: 737026 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0265. Min Act: -0.0001

Data Index: 58834 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0303. Min Act: -0.0001

Data Index: 1076241 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0323. Min Act: -0.0001

Data Index: 720251 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0282. Min Act: -0.0001

Data Index: 1018642 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0315. Min Act: -0.0001

Data Index: 361774 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0283. Min Act: -0.0001

Data Index: 1102098 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0258. Min Act: -0.0001

Data Index: 1565279 (Python Code)

Max Activating Token Index: 324

Text #15

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0290. Min Act: -0.0001

Data Index: 514753 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0243. Min Act: -0.0001

Data Index: 246723 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0269. Min Act: -0.0001

Data Index: 1555209 (Python Code)

Max Activating Token Index: 530

Text #18

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0257. Min Act: -0.0001

Data Index: 375878 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0275. Min Act: -0.0001

Data Index: 138177 (C4 (Web Text))

Max Activating Token Index: 959