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

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

Neuron 1112 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0184. Min Act: -0.0004

Data Index: 1537568 (Python Code)

Max Activating Token Index: 373

Text #1

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0162. Min Act: -0.0004

Data Index: 201963 (C4 (Web Text))

Max Activating Token Index: 611

Text #2

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0162. Min Act: -0.0004

Data Index: 1557566 (Python Code)

Max Activating Token Index: 906

Text #3

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0168. Min Act: -0.0004

Data Index: 993761 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0168. Min Act: -0.0004

Data Index: 856408 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0141. Min Act: -0.0004

Data Index: 537176 (C4 (Web Text))

Max Activating Token Index: 335

Text #6

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0166. Min Act: -0.0004

Data Index: 1065448 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0141. Min Act: -0.0004

Data Index: 472919 (C4 (Web Text))

Max Activating Token Index: 1002

Text #8

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0153. Min Act: -0.0004

Data Index: 1333210 (C4 (Web Text))

Max Activating Token Index: 962

Text #9

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0156. Min Act: -0.0004

Data Index: 390617 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0145. Min Act: -0.0004

Data Index: 667982 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0146. Min Act: -0.0004

Data Index: 51136 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0156. Min Act: -0.0004

Data Index: 1048388 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0136. Min Act: -0.0004

Data Index: 963392 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0128. Min Act: -0.0004

Data Index: 435261 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0133. Min Act: -0.0004

Data Index: 103529 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0134. Min Act: -0.0004

Data Index: 502480 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0139. Min Act: -0.0004

Data Index: 1367812 (Python Code)

Max Activating Token Index: 204

Text #18

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0128. Min Act: -0.0004

Data Index: 1342973 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0130. Min Act: -0.0004

Data Index: 1144598 (C4 (Web Text))

Max Activating Token Index: 206