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

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

Neuron 251 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0226. Min Act: -0.0006

Data Index: 1451884 (Python Code)

Max Activating Token Index: 964

Text #1

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0207. Min Act: -0.0006

Data Index: 1548958 (Python Code)

Max Activating Token Index: 660

Text #2

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0182. Min Act: -0.0006

Data Index: 834297 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0170. Min Act: -0.0006

Data Index: 1000159 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0176. Min Act: -0.0006

Data Index: 390723 (C4 (Web Text))

Max Activating Token Index: 871

Text #5

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0177. Min Act: -0.0006

Data Index: 321102 (C4 (Web Text))

Max Activating Token Index: 478

Text #6

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0167. Min Act: -0.0006

Data Index: 619273 (C4 (Web Text))

Max Activating Token Index: 399

Text #7

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0155. Min Act: -0.0006

Data Index: 1171979 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0163. Min Act: -0.0006

Data Index: 529325 (C4 (Web Text))

Max Activating Token Index: 873

Text #9

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0163. Min Act: -0.0006

Data Index: 1468741 (Python Code)

Max Activating Token Index: 427

Text #10

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0159. Min Act: -0.0006

Data Index: 1453868 (Python Code)

Max Activating Token Index: 940

Text #11

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0162. Min Act: -0.0006

Data Index: 957354 (C4 (Web Text))

Max Activating Token Index: 3

Text #12

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0163. Min Act: -0.0006

Data Index: 1590272 (Python Code)

Max Activating Token Index: 63

Text #13

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0170. Min Act: -0.0006

Data Index: 1392864 (Python Code)

Max Activating Token Index: 245

Text #14

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0163. Min Act: -0.0006

Data Index: 1374775 (Python Code)

Max Activating Token Index: 948

Text #15

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0165. Min Act: -0.0006

Data Index: 211805 (C4 (Web Text))

Max Activating Token Index: 811

Text #16

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0161. Min Act: -0.0006

Data Index: 1582506 (Python Code)

Max Activating Token Index: 22

Text #17

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0156. Min Act: -0.0006

Data Index: 891525 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0157. Min Act: -0.0006

Data Index: 1417081 (Python Code)

Max Activating Token Index: 831

Text #19

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0160. Min Act: -0.0006

Data Index: 1560964 (Python Code)

Max Activating Token Index: 704