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

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

Neuron 2887 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: 0.0259. Min Range: -0.0259

Max Act: 0.0259. Min Act: -0.0001

Data Index: 1554527 (Python Code)

Max Activating Token Index: 760

Text #1

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0177. Min Act: -0.0002

Data Index: 1435115 (Python Code)

Max Activating Token Index: 1012

Text #2

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0169. Min Act: -0.0001

Data Index: 1484330 (Python Code)

Max Activating Token Index: 818

Text #3

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0168. Min Act: -0.0001

Data Index: 1432405 (Python Code)

Max Activating Token Index: 12

Text #4

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0168. Min Act: -0.0001

Data Index: 1496364 (Python Code)

Max Activating Token Index: 588

Text #5

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0167. Min Act: -0.0001

Data Index: 1471137 (Python Code)

Max Activating Token Index: 230

Text #6

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0168. Min Act: -0.0001

Data Index: 1402922 (Python Code)

Max Activating Token Index: 48

Text #7

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0165. Min Act: -0.0001

Data Index: 1631861 (Python Code)

Max Activating Token Index: 35

Text #8

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0165. Min Act: -0.0001

Data Index: 1602250 (Python Code)

Max Activating Token Index: 705

Text #9

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0165. Min Act: -0.0001

Data Index: 1577599 (Python Code)

Max Activating Token Index: 803

Text #10

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0163. Min Act: -0.0001

Data Index: 1376709 (Python Code)

Max Activating Token Index: 1012

Text #11

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0162. Min Act: -0.0001

Data Index: 1610591 (Python Code)

Max Activating Token Index: 484

Text #12

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0161. Min Act: -0.0001

Data Index: 1597290 (Python Code)

Max Activating Token Index: 103

Text #13

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0162. Min Act: -0.0001

Data Index: 729550 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0162. Min Act: -0.0001

Data Index: 1434204 (Python Code)

Max Activating Token Index: 533

Text #15

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0160. Min Act: -0.0001

Data Index: 1628443 (Python Code)

Max Activating Token Index: 71

Text #16

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0160. Min Act: -0.0001

Data Index: 1575222 (Python Code)

Max Activating Token Index: 537

Text #17

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0158. Min Act: -0.0001

Data Index: 1407587 (Python Code)

Max Activating Token Index: 113

Text #18

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0158. Min Act: -0.0001

Data Index: 950796 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0158. Min Act: -0.0001

Data Index: 1379847 (Python Code)

Max Activating Token Index: 619