Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4538 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.3232. Min Range: -2.3232

Max Act: 2.3232. Min Act: -0.0000

Data Index: 621049 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 2.3232. Min Range: -2.3232

Max Act: 2.1704. Min Act: 0.0000

Data Index: 1038943 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 2.3232. Min Range: -2.3232

Max Act: 2.1512. Min Act: 0.0000

Data Index: 646911 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 2.3232. Min Range: -2.3232

Max Act: 1.8906. Min Act: -0.0000

Data Index: 1186744 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 2.3232. Min Range: -2.3232

Max Act: 1.9762. Min Act: -0.0000

Data Index: 220678 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 2.3232. Min Range: -2.3232

Max Act: 2.0247. Min Act: -0.0000

Data Index: 607955 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 2.3232. Min Range: -2.3232

Max Act: 2.0074. Min Act: -0.0000

Data Index: 299303 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 2.3232. Min Range: -2.3232

Max Act: 1.9347. Min Act: -0.0000

Data Index: 1304447 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 2.3232. Min Range: -2.3232

Max Act: 1.9248. Min Act: -0.0000

Data Index: 1209849 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 2.3232. Min Range: -2.3232

Max Act: 1.9234. Min Act: 0.0000

Data Index: 1115937 (C4 (Web Text))

Max Activating Token Index: 873

Text #10

Max Range: 2.3232. Min Range: -2.3232

Max Act: 1.9139. Min Act: -0.0000

Data Index: 1203125 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 2.3232. Min Range: -2.3232

Max Act: 1.9091. Min Act: 0.0000

Data Index: 761265 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 2.3232. Min Range: -2.3232

Max Act: 1.8932. Min Act: -0.0000

Data Index: 413141 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 2.3232. Min Range: -2.3232

Max Act: 1.8532. Min Act: -0.0000

Data Index: 233165 (C4 (Web Text))

Max Activating Token Index: 462

Text #14

Max Range: 2.3232. Min Range: -2.3232

Max Act: 1.8124. Min Act: -0.0000

Data Index: 992445 (C4 (Web Text))

Max Activating Token Index: 670

Text #15

Max Range: 2.3232. Min Range: -2.3232

Max Act: 1.7297. Min Act: -0.0000

Data Index: 981332 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 2.3232. Min Range: -2.3232

Max Act: 1.8365. Min Act: -0.0000

Data Index: 1130570 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 2.3232. Min Range: -2.3232

Max Act: 1.9202. Min Act: -0.0000

Data Index: 1031909 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 2.3232. Min Range: -2.3232

Max Act: 1.8303. Min Act: -0.0000

Data Index: 15956 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 2.3232. Min Range: -2.3232

Max Act: 1.7124. Min Act: -0.0000

Data Index: 1198448 (C4 (Web Text))

Max Activating Token Index: 691