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

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

Neuron 1301 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: 0.4301. Min Range: -0.4301

Max Act: 0.4301. Min Act: -0.0001

Data Index: 11247 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.4221. Min Act: -0.0001

Data Index: 762271 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.4263. Min Act: -0.0001

Data Index: 689268 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.4167. Min Act: -0.0001

Data Index: 1002949 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.4174. Min Act: -0.0001

Data Index: 464123 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.4098. Min Act: -0.0001

Data Index: 338751 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.4098. Min Act: -0.0001

Data Index: 123830 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.4087. Min Act: -0.0001

Data Index: 274135 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.4088. Min Act: -0.0001

Data Index: 674304 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.4036. Min Act: -0.0001

Data Index: 1080740 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.4049. Min Act: -0.0001

Data Index: 188342 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.4035. Min Act: -0.0001

Data Index: 1275885 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.4067. Min Act: -0.0001

Data Index: 998693 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3968. Min Act: -0.0001

Data Index: 497049 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.4010. Min Act: -0.0001

Data Index: 1007844 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3957. Min Act: -0.0001

Data Index: 134450 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3927. Min Act: -0.0001

Data Index: 194304 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3978. Min Act: -0.0001

Data Index: 685441 (C4 (Web Text))

Max Activating Token Index: 55

Text #18

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3959. Min Act: -0.0001

Data Index: 231107 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3945. Min Act: -0.0001

Data Index: 113934 (C4 (Web Text))

Max Activating Token Index: 1023