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

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

Neuron 1937 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: 0.3628. Min Range: -0.3628

Max Act: 0.3628. Min Act: -0.0000

Data Index: 534946 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3476. Min Act: -0.0000

Data Index: 429793 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3550. Min Act: -0.0001

Data Index: 218830 (C4 (Web Text))

Max Activating Token Index: 908

Text #3

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3192. Min Act: -0.0000

Data Index: 1338400 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3392. Min Act: -0.0000

Data Index: 87515 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3330. Min Act: -0.0000

Data Index: 522557 (C4 (Web Text))

Max Activating Token Index: 288

Text #6

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3302. Min Act: -0.0000

Data Index: 207071 (C4 (Web Text))

Max Activating Token Index: 485

Text #7

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3303. Min Act: -0.0000

Data Index: 697668 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3172. Min Act: -0.0001

Data Index: 336822 (C4 (Web Text))

Max Activating Token Index: 1018

Text #9

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3227. Min Act: -0.0000

Data Index: 325673 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3209. Min Act: -0.0001

Data Index: 918898 (C4 (Web Text))

Max Activating Token Index: 1021

Text #11

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3313. Min Act: -0.0000

Data Index: 1027570 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3196. Min Act: -0.0001

Data Index: 947383 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3276. Min Act: -0.0000

Data Index: 432877 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3119. Min Act: -0.0000

Data Index: 693533 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3189. Min Act: -0.0000

Data Index: 797836 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.2946. Min Act: -0.0000

Data Index: 1133001 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.2929. Min Act: -0.0000

Data Index: 1096939 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.2934. Min Act: -0.0001

Data Index: 844498 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.2857. Min Act: -0.0001

Data Index: 1283042 (C4 (Web Text))

Max Activating Token Index: 131