Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 355 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2801. Min Act: -0.0001

Data Index: 543258 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2869. Min Act: -0.0001

Data Index: 398000 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2775. Min Act: -0.0001

Data Index: 376216 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2623. Min Act: -0.0001

Data Index: 1122945 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2499. Min Act: -0.0000

Data Index: 472955 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2389. Min Act: -0.0000

Data Index: 260187 (C4 (Web Text))

Max Activating Token Index: 933

Text #6

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2505. Min Act: -0.0001

Data Index: 478496 (C4 (Web Text))

Max Activating Token Index: 272

Text #7

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2349. Min Act: -0.0001

Data Index: 1184453 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2419. Min Act: -0.0001

Data Index: 606860 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2458. Min Act: -0.0001

Data Index: 1393576 (Python Code)

Max Activating Token Index: 613

Text #10

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2351. Min Act: -0.0001

Data Index: 207173 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2374. Min Act: -0.0001

Data Index: 264440 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2202. Min Act: -0.0001

Data Index: 1056804 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2335. Min Act: -0.0001

Data Index: 1178027 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2345. Min Act: -0.0001

Data Index: 71194 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2191. Min Act: -0.0001

Data Index: 679340 (C4 (Web Text))

Max Activating Token Index: 224

Text #16

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2179. Min Act: -0.0001

Data Index: 709419 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2335. Min Act: -0.0001

Data Index: 135966 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2170. Min Act: -0.0001

Data Index: 292815 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2302. Min Act: -0.0001

Data Index: 202525 (C4 (Web Text))

Max Activating Token Index: 376