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

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

Neuron 165 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4458. Min Range: -1.4458

Max Act: 1.4458. Min Act: -0.0001

Data Index: 1117875 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 1.4458. Min Range: -1.4458

Max Act: 1.1712. Min Act: -0.0000

Data Index: 637911 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 1.4458. Min Range: -1.4458

Max Act: 1.0709. Min Act: -0.0001

Data Index: 211483 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 1.4458. Min Range: -1.4458

Max Act: 1.0561. Min Act: -0.0000

Data Index: 1149182 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 1.4458. Min Range: -1.4458

Max Act: 1.0431. Min Act: -0.0000

Data Index: 494567 (C4 (Web Text))

Max Activating Token Index: 920

Text #5

Max Range: 1.4458. Min Range: -1.4458

Max Act: 1.0957. Min Act: -0.0001

Data Index: 1106807 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 1.4458. Min Range: -1.4458

Max Act: 0.9587. Min Act: -0.0001

Data Index: 418073 (C4 (Web Text))

Max Activating Token Index: 178

Text #7

Max Range: 1.4458. Min Range: -1.4458

Max Act: 0.9311. Min Act: -0.0001

Data Index: 583767 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 1.4458. Min Range: -1.4458

Max Act: 0.8966. Min Act: -0.0001

Data Index: 735220 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 1.4458. Min Range: -1.4458

Max Act: 0.9236. Min Act: -0.0001

Data Index: 981998 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 1.4458. Min Range: -1.4458

Max Act: 0.8896. Min Act: -0.0001

Data Index: 640435 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 1.4458. Min Range: -1.4458

Max Act: 0.9209. Min Act: -0.0000

Data Index: 510612 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 1.4458. Min Range: -1.4458

Max Act: 0.9451. Min Act: -0.0001

Data Index: 499271 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 1.4458. Min Range: -1.4458

Max Act: 0.9109. Min Act: -0.0000

Data Index: 744824 (C4 (Web Text))

Max Activating Token Index: 776

Text #14

Max Range: 1.4458. Min Range: -1.4458

Max Act: 0.9747. Min Act: -0.0001

Data Index: 185294 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 1.4458. Min Range: -1.4458

Max Act: 0.8322. Min Act: -0.0000

Data Index: 1073976 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 1.4458. Min Range: -1.4458

Max Act: 0.8581. Min Act: -0.0001

Data Index: 1532800 (Python Code)

Max Activating Token Index: 134

Text #17

Max Range: 1.4458. Min Range: -1.4458

Max Act: 0.8831. Min Act: -0.0001

Data Index: 114211 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 1.4458. Min Range: -1.4458

Max Act: 0.8408. Min Act: -0.0000

Data Index: 1009877 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 1.4458. Min Range: -1.4458

Max Act: 0.8411. Min Act: -0.0001

Data Index: 132761 (C4 (Web Text))

Max Activating Token Index: 962