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

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

Neuron 4851 in Layer 1

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: 0.0225. Min Range: -0.0225

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1446171 (Python Code)

Max Activating Token Index: 611

Text #1

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0165. Min Act: -0.0002

Data Index: 1438571 (Python Code)

Max Activating Token Index: 17

Text #2

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0163. Min Act: -0.0002

Data Index: 762589 (C4 (Web Text))

Max Activating Token Index: 989

Text #3

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0159. Min Act: -0.0002

Data Index: 1408536 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0152. Min Act: -0.0002

Data Index: 1481599 (Python Code)

Max Activating Token Index: 860

Text #5

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0148. Min Act: -0.0002

Data Index: 325450 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0148. Min Act: -0.0002

Data Index: 663542 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0147. Min Act: -0.0002

Data Index: 1275721 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0145. Min Act: -0.0002

Data Index: 300708 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1655521 (Python Code)

Max Activating Token Index: 20

Text #10

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0138. Min Act: -0.0002

Data Index: 595296 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0136. Min Act: -0.0002

Data Index: 1479813 (Python Code)

Max Activating Token Index: 927

Text #12

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0136. Min Act: -0.0002

Data Index: 1544070 (Python Code)

Max Activating Token Index: 647

Text #13

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0134. Min Act: -0.0002

Data Index: 1493302 (Python Code)

Max Activating Token Index: 870

Text #14

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1426156 (Python Code)

Max Activating Token Index: 436

Text #15

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0137. Min Act: -0.0002

Data Index: 393170 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0134. Min Act: -0.0002

Data Index: 1617623 (Python Code)

Max Activating Token Index: 893

Text #17

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0133. Min Act: -0.0002

Data Index: 1535919 (Python Code)

Max Activating Token Index: 676

Text #18

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0134. Min Act: -0.0002

Data Index: 323684 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0136. Min Act: -0.0002

Data Index: 26778 (C4 (Web Text))

Max Activating Token Index: 82