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

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

Neuron 2705 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.5174. Min Act: -0.0001

Data Index: 1029510 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4676. Min Act: -0.0001

Data Index: 592265 (C4 (Web Text))

Max Activating Token Index: 481

Text #2

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4539. Min Act: -0.0001

Data Index: 1316729 (C4 (Web Text))

Max Activating Token Index: 334

Text #3

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4773. Min Act: -0.0001

Data Index: 859201 (C4 (Web Text))

Max Activating Token Index: 458

Text #4

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4390. Min Act: -0.0001

Data Index: 1158746 (C4 (Web Text))

Max Activating Token Index: 458

Text #5

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4082. Min Act: -0.0001

Data Index: 390082 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4602. Min Act: -0.0001

Data Index: 38791 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4489. Min Act: -0.0001

Data Index: 28401 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4267. Min Act: -0.0001

Data Index: 585042 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4440. Min Act: -0.0001

Data Index: 281890 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4491. Min Act: -0.0001

Data Index: 340018 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4232. Min Act: -0.0001

Data Index: 955548 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4182. Min Act: -0.0001

Data Index: 549103 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4245. Min Act: -0.0001

Data Index: 181042 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4422. Min Act: -0.0001

Data Index: 1290377 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4351. Min Act: -0.0001

Data Index: 1171689 (C4 (Web Text))

Max Activating Token Index: 321

Text #16

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4390. Min Act: -0.0001

Data Index: 1228326 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4351. Min Act: -0.0001

Data Index: 230268 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4197. Min Act: -0.0001

Data Index: 12959 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4043. Min Act: -0.0001

Data Index: 836481 (C4 (Web Text))

Max Activating Token Index: 420