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

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

Neuron 1035 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2827. Min Act: -0.0001

Data Index: 898274 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.3107. Min Act: -0.0001

Data Index: 1112275 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2684. Min Act: -0.0001

Data Index: 817728 (C4 (Web Text))

Max Activating Token Index: 533

Text #3

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2480. Min Act: -0.0001

Data Index: 969423 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2531. Min Act: -0.0001

Data Index: 800066 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2497. Min Act: -0.0001

Data Index: 724205 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2412. Min Act: -0.0001

Data Index: 1011312 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2449. Min Act: -0.0001

Data Index: 620525 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2443. Min Act: -0.0001

Data Index: 601747 (C4 (Web Text))

Max Activating Token Index: 997

Text #9

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2314. Min Act: -0.0001

Data Index: 849918 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2291. Min Act: -0.0001

Data Index: 300405 (C4 (Web Text))

Max Activating Token Index: 602

Text #11

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2254. Min Act: -0.0001

Data Index: 793655 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2231. Min Act: -0.0001

Data Index: 266886 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2198. Min Act: -0.0001

Data Index: 1303092 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2337. Min Act: -0.0001

Data Index: 362875 (C4 (Web Text))

Max Activating Token Index: 866

Text #15

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2252. Min Act: -0.0001

Data Index: 1049832 (C4 (Web Text))

Max Activating Token Index: 418

Text #16

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2245. Min Act: -0.0001

Data Index: 582345 (C4 (Web Text))

Max Activating Token Index: 480

Text #17

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2246. Min Act: -0.0001

Data Index: 917532 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2229. Min Act: -0.0001

Data Index: 134740 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2213. Min Act: -0.0001

Data Index: 508973 (C4 (Web Text))

Max Activating Token Index: 821