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

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

Neuron 1085 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: 1.2597. Min Range: -1.2597

Max Act: 1.2597. Min Act: -0.0002

Data Index: 859480 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 1.2597. Min Range: -1.2597

Max Act: 1.2175. Min Act: -0.0002

Data Index: 60644 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 1.2597. Min Range: -1.2597

Max Act: 1.1593. Min Act: -0.0002

Data Index: 801111 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 1.2597. Min Range: -1.2597

Max Act: 1.1261. Min Act: -0.0002

Data Index: 1050563 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 1.2597. Min Range: -1.2597

Max Act: 1.0672. Min Act: -0.0002

Data Index: 360308 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 1.2597. Min Range: -1.2597

Max Act: 1.0289. Min Act: -0.0002

Data Index: 489141 (C4 (Web Text))

Max Activating Token Index: 764

Text #6

Max Range: 1.2597. Min Range: -1.2597

Max Act: 1.0573. Min Act: -0.0002

Data Index: 1278546 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 1.2597. Min Range: -1.2597

Max Act: 1.0365. Min Act: -0.0002

Data Index: 1197604 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 1.2597. Min Range: -1.2597

Max Act: 1.0166. Min Act: -0.0002

Data Index: 438449 (C4 (Web Text))

Max Activating Token Index: 1010

Text #9

Max Range: 1.2597. Min Range: -1.2597

Max Act: 1.0203. Min Act: -0.0002

Data Index: 698181 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 1.2597. Min Range: -1.2597

Max Act: 1.0172. Min Act: -0.0002

Data Index: 200020 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 1.2597. Min Range: -1.2597

Max Act: 1.0227. Min Act: -0.0002

Data Index: 112364 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 1.2597. Min Range: -1.2597

Max Act: 1.0025. Min Act: -0.0002

Data Index: 395553 (C4 (Web Text))

Max Activating Token Index: 473

Text #13

Max Range: 1.2597. Min Range: -1.2597

Max Act: 1.0067. Min Act: -0.0002

Data Index: 353674 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 1.2597. Min Range: -1.2597

Max Act: 1.0060. Min Act: -0.0002

Data Index: 201134 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 1.2597. Min Range: -1.2597

Max Act: 1.0047. Min Act: -0.0002

Data Index: 624807 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 1.2597. Min Range: -1.2597

Max Act: 1.0148. Min Act: -0.0002

Data Index: 406737 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 1.2597. Min Range: -1.2597

Max Act: 1.0090. Min Act: -0.0002

Data Index: 600144 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 1.2597. Min Range: -1.2597

Max Act: 0.9949. Min Act: -0.0002

Data Index: 538723 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 1.2597. Min Range: -1.2597

Max Act: 1.0144. Min Act: -0.0002

Data Index: 602907 (C4 (Web Text))

Max Activating Token Index: 62