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

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

Neuron 307 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: 0.1389. Min Range: -0.1389

Max Act: 0.1389. Min Act: -0.0001

Data Index: 1107759 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1281. Min Act: -0.0001

Data Index: 971316 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1218. Min Act: -0.0001

Data Index: 1297254 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1122. Min Act: -0.0001

Data Index: 784927 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1202. Min Act: -0.0001

Data Index: 582609 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1146. Min Act: -0.0001

Data Index: 604753 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1093. Min Act: -0.0000

Data Index: 1044131 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1054. Min Act: -0.0001

Data Index: 855297 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1027. Min Act: -0.0001

Data Index: 669740 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1140. Min Act: -0.0001

Data Index: 506130 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0962. Min Act: -0.0001

Data Index: 1350428 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0963. Min Act: -0.0001

Data Index: 466233 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0988. Min Act: -0.0001

Data Index: 278967 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0961. Min Act: -0.0001

Data Index: 1092134 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0958. Min Act: -0.0001

Data Index: 504736 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0936. Min Act: -0.0001

Data Index: 1169068 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0993. Min Act: -0.0001

Data Index: 60280 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0920. Min Act: -0.0001

Data Index: 247276 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0945. Min Act: -0.0001

Data Index: 302011 (C4 (Web Text))

Max Activating Token Index: 388

Text #19

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0922. Min Act: -0.0001

Data Index: 918319 (C4 (Web Text))

Max Activating Token Index: 62