Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2123 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0218. Min Act: -0.0002

Data Index: 1588685 (Python Code)

Max Activating Token Index: 988

Text #1

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0164. Min Act: -0.0001

Data Index: 819964 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0173. Min Act: -0.0001

Data Index: 676039 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0151. Min Act: -0.0002

Data Index: 1610239 (Python Code)

Max Activating Token Index: 773

Text #4

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0152. Min Act: -0.0002

Data Index: 1377937 (Python Code)

Max Activating Token Index: 1004

Text #5

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0159. Min Act: -0.0001

Data Index: 347914 (C4 (Web Text))

Max Activating Token Index: 988

Text #6

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0132. Min Act: -0.0002

Data Index: 432541 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0151. Min Act: -0.0002

Data Index: 215253 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0149. Min Act: -0.0002

Data Index: 898714 (C4 (Web Text))

Max Activating Token Index: 965

Text #9

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0134. Min Act: -0.0001

Data Index: 56737 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0142. Min Act: -0.0001

Data Index: 487672 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0151. Min Act: -0.0002

Data Index: 260467 (C4 (Web Text))

Max Activating Token Index: 782

Text #12

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0138. Min Act: -0.0002

Data Index: 1494169 (Python Code)

Max Activating Token Index: 936

Text #13

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0135. Min Act: -0.0002

Data Index: 1417145 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0127. Min Act: -0.0002

Data Index: 745402 (C4 (Web Text))

Max Activating Token Index: 991

Text #15

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0145. Min Act: -0.0001

Data Index: 514706 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0135. Min Act: -0.0002

Data Index: 96813 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0132. Min Act: -0.0001

Data Index: 914436 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0131. Min Act: -0.0002

Data Index: 56538 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0141. Min Act: -0.0002

Data Index: 1532989 (Python Code)

Max Activating Token Index: 828