Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4884 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2422. Min Range: -1.2422

Max Act: 1.2422. Min Act: -0.0000

Data Index: 282058 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 1.2422. Min Range: -1.2422

Max Act: 1.1410. Min Act: -0.0000

Data Index: 863166 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 1.2422. Min Range: -1.2422

Max Act: 1.0744. Min Act: -0.0000

Data Index: 399134 (C4 (Web Text))

Max Activating Token Index: 430

Text #3

Max Range: 1.2422. Min Range: -1.2422

Max Act: 0.9655. Min Act: -0.0000

Data Index: 1105616 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 1.2422. Min Range: -1.2422

Max Act: 0.8963. Min Act: -0.0000

Data Index: 991324 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 1.2422. Min Range: -1.2422

Max Act: 0.9968. Min Act: -0.0000

Data Index: 293809 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 1.2422. Min Range: -1.2422

Max Act: 0.9912. Min Act: -0.0000

Data Index: 448483 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 1.2422. Min Range: -1.2422

Max Act: 0.9761. Min Act: -0.0000

Data Index: 91264 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 1.2422. Min Range: -1.2422

Max Act: 0.9725. Min Act: -0.0000

Data Index: 141967 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 1.2422. Min Range: -1.2422

Max Act: 0.9813. Min Act: -0.0000

Data Index: 1107538 (C4 (Web Text))

Max Activating Token Index: 869

Text #10

Max Range: 1.2422. Min Range: -1.2422

Max Act: 0.8980. Min Act: -0.0000

Data Index: 526955 (C4 (Web Text))

Max Activating Token Index: 905

Text #11

Max Range: 1.2422. Min Range: -1.2422

Max Act: 0.7638. Min Act: -0.0000

Data Index: 199704 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 1.2422. Min Range: -1.2422

Max Act: 0.8238. Min Act: -0.0000

Data Index: 214652 (C4 (Web Text))

Max Activating Token Index: 202

Text #13

Max Range: 1.2422. Min Range: -1.2422

Max Act: 0.8031. Min Act: -0.0000

Data Index: 286970 (C4 (Web Text))

Max Activating Token Index: 1001

Text #14

Max Range: 1.2422. Min Range: -1.2422

Max Act: 0.8267. Min Act: -0.0000

Data Index: 1272786 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 1.2422. Min Range: -1.2422

Max Act: 0.8612. Min Act: -0.0000

Data Index: 1311967 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 1.2422. Min Range: -1.2422

Max Act: 0.8429. Min Act: -0.0000

Data Index: 617874 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 1.2422. Min Range: -1.2422

Max Act: 0.8034. Min Act: -0.0000

Data Index: 794289 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 1.2422. Min Range: -1.2422

Max Act: 0.8002. Min Act: -0.0000

Data Index: 519641 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 1.2422. Min Range: -1.2422

Max Act: 0.7791. Min Act: -0.0000

Data Index: 1285293 (C4 (Web Text))

Max Activating Token Index: 994