Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1989 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0168. Min Act: -0.0001

Data Index: 697633 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0165. Min Act: -0.0001

Data Index: 5921 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0165. Min Act: -0.0001

Data Index: 46203 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0164. Min Act: -0.0001

Data Index: 354014 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0162. Min Act: -0.0001

Data Index: 122927 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0160. Min Act: -0.0001

Data Index: 379360 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0161. Min Act: -0.0001

Data Index: 581564 (C4 (Web Text))

Max Activating Token Index: 305

Text #7

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0156. Min Act: -0.0001

Data Index: 1084642 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0156. Min Act: -0.0001

Data Index: 149503 (C4 (Web Text))

Max Activating Token Index: 376

Text #9

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0154. Min Act: -0.0001

Data Index: 443800 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0150. Min Act: -0.0001

Data Index: 322339 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0152. Min Act: -0.0002

Data Index: 8792 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0150. Min Act: -0.0001

Data Index: 1066634 (C4 (Web Text))

Max Activating Token Index: 2

Text #13

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0149. Min Act: -0.0001

Data Index: 1192434 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0149. Min Act: -0.0001

Data Index: 1512219 (Python Code)

Max Activating Token Index: 4

Text #15

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0148. Min Act: -0.0001

Data Index: 46269 (C4 (Web Text))

Max Activating Token Index: 512

Text #16

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0149. Min Act: -0.0001

Data Index: 1335008 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0146. Min Act: -0.0001

Data Index: 1120324 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0146. Min Act: -0.0001

Data Index: 1185737 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0144. Min Act: -0.0001

Data Index: 1193605 (C4 (Web Text))

Max Activating Token Index: 126