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

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

Neuron 6114 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: 0.0206. Min Range: -0.0206

Max Act: 0.0206. Min Act: -0.0001

Data Index: 545241 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0202. Min Act: -0.0002

Data Index: 1344793 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0200. Min Act: -0.0001

Data Index: 34581 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0191. Min Act: -0.0001

Data Index: 892101 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0193. Min Act: -0.0001

Data Index: 989025 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0188. Min Act: -0.0001

Data Index: 3265 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0186. Min Act: -0.0001

Data Index: 700267 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0186. Min Act: -0.0002

Data Index: 958781 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0182. Min Act: -0.0001

Data Index: 1342508 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0179. Min Act: -0.0001

Data Index: 1061990 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0178. Min Act: -0.0002

Data Index: 999178 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0175. Min Act: -0.0001

Data Index: 909430 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0176. Min Act: -0.0001

Data Index: 322011 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0174. Min Act: -0.0001

Data Index: 1358160 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0176. Min Act: -0.0001

Data Index: 1119275 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0174. Min Act: -0.0002

Data Index: 49880 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0174. Min Act: -0.0001

Data Index: 339000 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0176. Min Act: -0.0001

Data Index: 751064 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0174. Min Act: -0.0001

Data Index: 747368 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 0.0206. Min Range: -0.0206

Max Act: 0.0174. Min Act: -0.0001

Data Index: 1108389 (C4 (Web Text))

Max Activating Token Index: 1023