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

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

Neuron 3007 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: 0.8005. Min Range: -0.8005

Max Act: 0.8005. Min Act: -0.0000

Data Index: 324574 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.7164. Min Act: -0.0000

Data Index: 1274045 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.7268. Min Act: -0.0000

Data Index: 203935 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.6869. Min Act: -0.0000

Data Index: 1297417 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.7066. Min Act: -0.0000

Data Index: 425500 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.6845. Min Act: -0.0000

Data Index: 1316346 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.6305. Min Act: -0.0000

Data Index: 749893 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.6184. Min Act: -0.0000

Data Index: 499175 (C4 (Web Text))

Max Activating Token Index: 794

Text #8

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.6302. Min Act: -0.0000

Data Index: 79590 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.6219. Min Act: -0.0000

Data Index: 1286427 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.6230. Min Act: -0.0000

Data Index: 255202 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.6091. Min Act: -0.0000

Data Index: 535961 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.5755. Min Act: -0.0000

Data Index: 425363 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.5695. Min Act: -0.0000

Data Index: 249861 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.5505. Min Act: -0.0000

Data Index: 277212 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.5495. Min Act: -0.0000

Data Index: 528174 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.5401. Min Act: -0.0000

Data Index: 895463 (C4 (Web Text))

Max Activating Token Index: 403

Text #17

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.5188. Min Act: -0.0000

Data Index: 835006 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.5446. Min Act: -0.0000

Data Index: 596490 (C4 (Web Text))

Max Activating Token Index: 589

Text #19

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.5510. Min Act: -0.0000

Data Index: 131520 (C4 (Web Text))

Max Activating Token Index: 472