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

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

Neuron 1435 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: 0.2698. Min Range: -0.2698

Max Act: 0.2698. Min Act: -0.0001

Data Index: 865855 (C4 (Web Text))

Max Activating Token Index: 501

Text #1

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2610. Min Act: -0.0001

Data Index: 284442 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2362. Min Act: -0.0001

Data Index: 508182 (C4 (Web Text))

Max Activating Token Index: 704

Text #3

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2570. Min Act: -0.0001

Data Index: 1045682 (C4 (Web Text))

Max Activating Token Index: 305

Text #4

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2271. Min Act: -0.0001

Data Index: 1345230 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2327. Min Act: -0.0001

Data Index: 931196 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2301. Min Act: -0.0001

Data Index: 411547 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2308. Min Act: -0.0001

Data Index: 1286378 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2224. Min Act: -0.0001

Data Index: 627160 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2234. Min Act: -0.0001

Data Index: 110102 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2266. Min Act: -0.0001

Data Index: 614669 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2191. Min Act: -0.0001

Data Index: 95852 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2076. Min Act: -0.0001

Data Index: 1264246 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2116. Min Act: -0.0001

Data Index: 1088056 (C4 (Web Text))

Max Activating Token Index: 604

Text #14

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2070. Min Act: -0.0001

Data Index: 1094751 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.1975. Min Act: -0.0001

Data Index: 633087 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2090. Min Act: -0.0001

Data Index: 310447 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2092. Min Act: -0.0001

Data Index: 1272828 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2053. Min Act: -0.0000

Data Index: 584802 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.1965. Min Act: -0.0001

Data Index: 765050 (C4 (Web Text))

Max Activating Token Index: 1016