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

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

Neuron 2051 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: 0.5968. Min Range: -0.5968

Max Act: 0.5968. Min Act: -0.0001

Data Index: 1163083 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.5748. Min Act: -0.0001

Data Index: 405308 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.5777. Min Act: -0.0001

Data Index: 773637 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.5661. Min Act: -0.0001

Data Index: 223433 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.5469. Min Act: -0.0001

Data Index: 58094 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.5365. Min Act: -0.0001

Data Index: 4151 (C4 (Web Text))

Max Activating Token Index: 968

Text #6

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.5339. Min Act: -0.0001

Data Index: 880014 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.5372. Min Act: -0.0001

Data Index: 1199261 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.5363. Min Act: -0.0001

Data Index: 1256186 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.5245. Min Act: -0.0001

Data Index: 294516 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.5264. Min Act: -0.0001

Data Index: 216529 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.5189. Min Act: -0.0001

Data Index: 1150125 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.5209. Min Act: -0.0001

Data Index: 557380 (C4 (Web Text))

Max Activating Token Index: 3

Text #13

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.5217. Min Act: -0.0001

Data Index: 926757 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.5320. Min Act: -0.0001

Data Index: 1114481 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.5303. Min Act: -0.0001

Data Index: 1041371 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.5270. Min Act: -0.0001

Data Index: 967700 (C4 (Web Text))

Max Activating Token Index: 968

Text #17

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.5197. Min Act: -0.0001

Data Index: 1218205 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.5260. Min Act: -0.0001

Data Index: 350799 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.5147. Min Act: -0.0001

Data Index: 863059 (C4 (Web Text))

Max Activating Token Index: 358