Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 655 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.3145. Min Act: -0.0002

Data Index: 1263036 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2791. Min Act: -0.0002

Data Index: 82366 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2810. Min Act: -0.0002

Data Index: 913058 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2583. Min Act: -0.0002

Data Index: 580283 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2520. Min Act: -0.0002

Data Index: 990550 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2478. Min Act: -0.0002

Data Index: 904317 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2316. Min Act: -0.0002

Data Index: 1176788 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2311. Min Act: -0.0002

Data Index: 449476 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2280. Min Act: -0.0002

Data Index: 611675 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2334. Min Act: -0.0002

Data Index: 926964 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2275. Min Act: -0.0002

Data Index: 508478 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2223. Min Act: -0.0002

Data Index: 20325 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2178. Min Act: -0.0002

Data Index: 114362 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2106. Min Act: -0.0002

Data Index: 453029 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2258. Min Act: -0.0002

Data Index: 171692 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2038. Min Act: -0.0002

Data Index: 644659 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.1924. Min Act: -0.0002

Data Index: 569954 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2081. Min Act: -0.0002

Data Index: 1338950 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.1977. Min Act: -0.0001

Data Index: 335531 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2034. Min Act: -0.0002

Data Index: 859150 (C4 (Web Text))

Max Activating Token Index: 1023