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

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

Neuron 3064 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1570. Min Act: -0.0001

Data Index: 20491 (C4 (Web Text))

Max Activating Token Index: 862

Text #1

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1227. Min Act: -0.0001

Data Index: 397768 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1250. Min Act: -0.0001

Data Index: 578073 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1163. Min Act: -0.0001

Data Index: 6062 (C4 (Web Text))

Max Activating Token Index: 364

Text #4

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1234. Min Act: -0.0001

Data Index: 506539 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1232. Min Act: -0.0001

Data Index: 79669 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1221. Min Act: -0.0001

Data Index: 731155 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1253. Min Act: -0.0001

Data Index: 237714 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1141. Min Act: -0.0001

Data Index: 1188279 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1112. Min Act: -0.0001

Data Index: 540604 (C4 (Web Text))

Max Activating Token Index: 526

Text #10

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1148. Min Act: -0.0001

Data Index: 1224539 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1152. Min Act: -0.0001

Data Index: 514101 (C4 (Web Text))

Max Activating Token Index: 933

Text #12

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1101. Min Act: -0.0001

Data Index: 850822 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1088. Min Act: -0.0001

Data Index: 309888 (C4 (Web Text))

Max Activating Token Index: 447

Text #14

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1112. Min Act: -0.0000

Data Index: 567669 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1105. Min Act: 0.0000

Data Index: 23408 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1012. Min Act: -0.0001

Data Index: 1020612 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1083. Min Act: -0.0001

Data Index: 255327 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1089. Min Act: -0.0001

Data Index: 100436 (C4 (Web Text))

Max Activating Token Index: 491

Text #19

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1045. Min Act: -0.0001

Data Index: 1176222 (C4 (Web Text))

Max Activating Token Index: 72