Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1521 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7828. Min Range: -1.7828

Max Act: 1.7828. Min Act: -0.0001

Data Index: 375427 (C4 (Web Text))

Max Activating Token Index: 240

Text #1

Max Range: 1.7828. Min Range: -1.7828

Max Act: 1.6907. Min Act: -0.0001

Data Index: 783930 (C4 (Web Text))

Max Activating Token Index: 507

Text #2

Max Range: 1.7828. Min Range: -1.7828

Max Act: 1.7140. Min Act: -0.0001

Data Index: 498522 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 1.7828. Min Range: -1.7828

Max Act: 1.3520. Min Act: -0.0001

Data Index: 66413 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 1.7828. Min Range: -1.7828

Max Act: 1.4747. Min Act: -0.0001

Data Index: 344465 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 1.7828. Min Range: -1.7828

Max Act: 1.4633. Min Act: -0.0001

Data Index: 20575 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 1.7828. Min Range: -1.7828

Max Act: 1.2172. Min Act: -0.0001

Data Index: 939539 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 1.7828. Min Range: -1.7828

Max Act: 1.4040. Min Act: -0.0001

Data Index: 1024065 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 1.7828. Min Range: -1.7828

Max Act: 1.5159. Min Act: -0.0001

Data Index: 893928 (C4 (Web Text))

Max Activating Token Index: 899

Text #9

Max Range: 1.7828. Min Range: -1.7828

Max Act: 1.3426. Min Act: -0.0001

Data Index: 1188797 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 1.7828. Min Range: -1.7828

Max Act: 1.3310. Min Act: -0.0001

Data Index: 958497 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 1.7828. Min Range: -1.7828

Max Act: 1.3162. Min Act: -0.0001

Data Index: 1182508 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 1.7828. Min Range: -1.7828

Max Act: 1.1517. Min Act: -0.0001

Data Index: 261392 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 1.7828. Min Range: -1.7828

Max Act: 1.2519. Min Act: -0.0001

Data Index: 448479 (C4 (Web Text))

Max Activating Token Index: 433

Text #14

Max Range: 1.7828. Min Range: -1.7828

Max Act: 1.2320. Min Act: -0.0001

Data Index: 151672 (C4 (Web Text))

Max Activating Token Index: 795

Text #15

Max Range: 1.7828. Min Range: -1.7828

Max Act: 1.1344. Min Act: -0.0001

Data Index: 924966 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 1.7828. Min Range: -1.7828

Max Act: 1.1939. Min Act: -0.0001

Data Index: 105272 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 1.7828. Min Range: -1.7828

Max Act: 1.2875. Min Act: -0.0001

Data Index: 127519 (C4 (Web Text))

Max Activating Token Index: 678

Text #18

Max Range: 1.7828. Min Range: -1.7828

Max Act: 1.1741. Min Act: -0.0001

Data Index: 592378 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 1.7828. Min Range: -1.7828

Max Act: 1.2586. Min Act: -0.0001

Data Index: 506004 (C4 (Web Text))

Max Activating Token Index: 729