Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 63 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0141. Min Act: -0.0006

Data Index: 273219 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0138. Min Act: -0.0006

Data Index: 976665 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0138. Min Act: -0.0006

Data Index: 653830 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0140. Min Act: -0.0006

Data Index: 816444 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0134. Min Act: -0.0006

Data Index: 1305430 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0135. Min Act: -0.0006

Data Index: 906376 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0133. Min Act: -0.0006

Data Index: 749469 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0136. Min Act: -0.0006

Data Index: 328850 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0134. Min Act: -0.0006

Data Index: 1265200 (C4 (Web Text))

Max Activating Token Index: 838

Text #9

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0134. Min Act: -0.0006

Data Index: 1011910 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0134. Min Act: -0.0006

Data Index: 385535 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0133. Min Act: -0.0006

Data Index: 855021 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0132. Min Act: -0.0006

Data Index: 320542 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0132. Min Act: -0.0006

Data Index: 172971 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0135. Min Act: -0.0006

Data Index: 1329085 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0130. Min Act: -0.0006

Data Index: 215592 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0131. Min Act: -0.0006

Data Index: 747639 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0131. Min Act: -0.0006

Data Index: 266489 (C4 (Web Text))

Max Activating Token Index: 761

Text #18

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0133. Min Act: -0.0006

Data Index: 1245127 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0131. Min Act: -0.0006

Data Index: 456339 (C4 (Web Text))

Max Activating Token Index: 466