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

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

Neuron 3534 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5401. Min Range: -0.5401

Max Act: 0.5401. Min Act: -0.0001

Data Index: 902312 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 0.5401. Min Range: -0.5401

Max Act: 0.5202. Min Act: -0.0001

Data Index: 723866 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 0.5401. Min Range: -0.5401

Max Act: 0.5171. Min Act: -0.0001

Data Index: 426219 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 0.5401. Min Range: -0.5401

Max Act: 0.4901. Min Act: -0.0001

Data Index: 1152297 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 0.5401. Min Range: -0.5401

Max Act: 0.4992. Min Act: -0.0001

Data Index: 817472 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 0.5401. Min Range: -0.5401

Max Act: 0.4801. Min Act: -0.0001

Data Index: 1284618 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 0.5401. Min Range: -0.5401

Max Act: 0.4471. Min Act: -0.0001

Data Index: 16412 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 0.5401. Min Range: -0.5401

Max Act: 0.4733. Min Act: -0.0001

Data Index: 116993 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 0.5401. Min Range: -0.5401

Max Act: 0.4559. Min Act: -0.0001

Data Index: 925763 (C4 (Web Text))

Max Activating Token Index: 319

Text #9

Max Range: 0.5401. Min Range: -0.5401

Max Act: 0.4441. Min Act: -0.0001

Data Index: 1230628 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 0.5401. Min Range: -0.5401

Max Act: 0.4304. Min Act: -0.0001

Data Index: 1057832 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 0.5401. Min Range: -0.5401

Max Act: 0.4282. Min Act: -0.0001

Data Index: 1122263 (C4 (Web Text))

Max Activating Token Index: 458

Text #12

Max Range: 0.5401. Min Range: -0.5401

Max Act: 0.4261. Min Act: -0.0001

Data Index: 73774 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 0.5401. Min Range: -0.5401

Max Act: 0.4207. Min Act: -0.0001

Data Index: 735755 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 0.5401. Min Range: -0.5401

Max Act: 0.4244. Min Act: -0.0001

Data Index: 626337 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 0.5401. Min Range: -0.5401

Max Act: 0.4209. Min Act: -0.0001

Data Index: 925816 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 0.5401. Min Range: -0.5401

Max Act: 0.4185. Min Act: -0.0001

Data Index: 929439 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 0.5401. Min Range: -0.5401

Max Act: 0.4003. Min Act: -0.0001

Data Index: 906045 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 0.5401. Min Range: -0.5401

Max Act: 0.4126. Min Act: -0.0001

Data Index: 44758 (C4 (Web Text))

Max Activating Token Index: 843

Text #19

Max Range: 0.5401. Min Range: -0.5401

Max Act: 0.4114. Min Act: -0.0001

Data Index: 307172 (C4 (Web Text))

Max Activating Token Index: 555