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

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

Neuron 6093 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: 0.3993. Min Range: -0.3993

Max Act: 0.3993. Min Act: -0.0001

Data Index: 83425 (C4 (Web Text))

Max Activating Token Index: 190

Text #1

Max Range: 0.3993. Min Range: -0.3993

Max Act: 0.3602. Min Act: -0.0001

Data Index: 132337 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 0.3993. Min Range: -0.3993

Max Act: 0.3550. Min Act: -0.0001

Data Index: 850231 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 0.3993. Min Range: -0.3993

Max Act: 0.3469. Min Act: -0.0001

Data Index: 388731 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 0.3993. Min Range: -0.3993

Max Act: 0.3359. Min Act: -0.0001

Data Index: 303510 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 0.3993. Min Range: -0.3993

Max Act: 0.3334. Min Act: -0.0001

Data Index: 561596 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 0.3993. Min Range: -0.3993

Max Act: 0.3268. Min Act: -0.0001

Data Index: 630768 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 0.3993. Min Range: -0.3993

Max Act: 0.3269. Min Act: -0.0001

Data Index: 188859 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 0.3993. Min Range: -0.3993

Max Act: 0.3285. Min Act: -0.0001

Data Index: 623203 (C4 (Web Text))

Max Activating Token Index: 598

Text #9

Max Range: 0.3993. Min Range: -0.3993

Max Act: 0.3179. Min Act: -0.0001

Data Index: 839108 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 0.3993. Min Range: -0.3993

Max Act: 0.3139. Min Act: -0.0001

Data Index: 164795 (C4 (Web Text))

Max Activating Token Index: 403

Text #11

Max Range: 0.3993. Min Range: -0.3993

Max Act: 0.3178. Min Act: -0.0001

Data Index: 1267699 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 0.3993. Min Range: -0.3993

Max Act: 0.3136. Min Act: -0.0001

Data Index: 1212118 (C4 (Web Text))

Max Activating Token Index: 544

Text #13

Max Range: 0.3993. Min Range: -0.3993

Max Act: 0.3058. Min Act: -0.0001

Data Index: 731228 (C4 (Web Text))

Max Activating Token Index: 747

Text #14

Max Range: 0.3993. Min Range: -0.3993

Max Act: 0.3041. Min Act: -0.0001

Data Index: 895810 (C4 (Web Text))

Max Activating Token Index: 415

Text #15

Max Range: 0.3993. Min Range: -0.3993

Max Act: 0.3092. Min Act: -0.0001

Data Index: 666538 (C4 (Web Text))

Max Activating Token Index: 178

Text #16

Max Range: 0.3993. Min Range: -0.3993

Max Act: 0.3108. Min Act: -0.0001

Data Index: 575083 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 0.3993. Min Range: -0.3993

Max Act: 0.3060. Min Act: -0.0001

Data Index: 296224 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 0.3993. Min Range: -0.3993

Max Act: 0.3022. Min Act: -0.0001

Data Index: 1240131 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 0.3993. Min Range: -0.3993

Max Act: 0.2975. Min Act: -0.0001

Data Index: 1196220 (C4 (Web Text))

Max Activating Token Index: 306