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

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

Neuron 2840 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.5312. Min Act: -0.0001

Data Index: 1158307 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.4413. Min Act: -0.0001

Data Index: 1112176 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.4574. Min Act: -0.0001

Data Index: 260777 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.4263. Min Act: -0.0001

Data Index: 1277972 (C4 (Web Text))

Max Activating Token Index: 996

Text #4

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.4138. Min Act: -0.0001

Data Index: 332787 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.4071. Min Act: -0.0001

Data Index: 239153 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.4046. Min Act: -0.0001

Data Index: 1253696 (C4 (Web Text))

Max Activating Token Index: 419

Text #7

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.4057. Min Act: -0.0001

Data Index: 427825 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.4059. Min Act: -0.0001

Data Index: 429225 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.3866. Min Act: -0.0001

Data Index: 829897 (C4 (Web Text))

Max Activating Token Index: 959

Text #10

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.4233. Min Act: -0.0001

Data Index: 52802 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.3768. Min Act: -0.0001

Data Index: 1046518 (C4 (Web Text))

Max Activating Token Index: 914

Text #12

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.3645. Min Act: -0.0001

Data Index: 470368 (C4 (Web Text))

Max Activating Token Index: 698

Text #13

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.3888. Min Act: -0.0001

Data Index: 1152456 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.3880. Min Act: -0.0001

Data Index: 517156 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.3990. Min Act: -0.0001

Data Index: 368216 (C4 (Web Text))

Max Activating Token Index: 436

Text #16

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.4003. Min Act: -0.0001

Data Index: 485831 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.3609. Min Act: -0.0001

Data Index: 174711 (C4 (Web Text))

Max Activating Token Index: 497

Text #18

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.3844. Min Act: -0.0001

Data Index: 702218 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 0.5312. Min Range: -0.5312

Max Act: 0.3573. Min Act: -0.0001

Data Index: 737252 (C4 (Web Text))

Max Activating Token Index: 223