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

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

Neuron 3386 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.9894. Min Act: -0.0000

Data Index: 765545 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 1.0056. Min Range: -1.0056

Max Act: 1.0056. Min Act: -0.0000

Data Index: 433479 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.9552. Min Act: -0.0000

Data Index: 982251 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.9444. Min Act: -0.0000

Data Index: 1090619 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.9466. Min Act: 0.0000

Data Index: 221111 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.8730. Min Act: -0.0000

Data Index: 1337351 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.8994. Min Act: -0.0000

Data Index: 1065256 (C4 (Web Text))

Max Activating Token Index: 669

Text #7

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.8900. Min Act: -0.0000

Data Index: 732575 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.8553. Min Act: -0.0000

Data Index: 545088 (C4 (Web Text))

Max Activating Token Index: 565

Text #9

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.8442. Min Act: -0.0000

Data Index: 1162256 (C4 (Web Text))

Max Activating Token Index: 372

Text #10

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.7722. Min Act: -0.0000

Data Index: 529190 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.7860. Min Act: -0.0000

Data Index: 1200833 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.7188. Min Act: -0.0000

Data Index: 96720 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.7593. Min Act: 0.0002

Data Index: 716813 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.7170. Min Act: -0.0000

Data Index: 1256677 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.7090. Min Act: -0.0000

Data Index: 547245 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.7043. Min Act: -0.0000

Data Index: 816597 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.7264. Min Act: -0.0000

Data Index: 839799 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.6979. Min Act: -0.0000

Data Index: 323611 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.7194. Min Act: 0.0000

Data Index: 883805 (C4 (Web Text))

Max Activating Token Index: 1014