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

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

Neuron 5289 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9013. Min Range: -0.9013

Max Act: 0.9013. Min Act: -0.0001

Data Index: 429770 (C4 (Web Text))

Max Activating Token Index: 732

Text #1

Max Range: 0.9013. Min Range: -0.9013

Max Act: 0.4933. Min Act: -0.0001

Data Index: 35644 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 0.9013. Min Range: -0.9013

Max Act: 0.4806. Min Act: -0.0001

Data Index: 1193027 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 0.9013. Min Range: -0.9013

Max Act: 0.4509. Min Act: -0.0001

Data Index: 397186 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 0.9013. Min Range: -0.9013

Max Act: 0.5142. Min Act: -0.0001

Data Index: 616308 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 0.9013. Min Range: -0.9013

Max Act: 0.4932. Min Act: -0.0001

Data Index: 370676 (C4 (Web Text))

Max Activating Token Index: 282

Text #6

Max Range: 0.9013. Min Range: -0.9013

Max Act: 0.4745. Min Act: -0.0001

Data Index: 283697 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 0.9013. Min Range: -0.9013

Max Act: 0.4538. Min Act: -0.0000

Data Index: 673442 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 0.9013. Min Range: -0.9013

Max Act: 0.4412. Min Act: -0.0001

Data Index: 553500 (C4 (Web Text))

Max Activating Token Index: 623

Text #9

Max Range: 0.9013. Min Range: -0.9013

Max Act: 0.4445. Min Act: -0.0001

Data Index: 1365950 (Python Code)

Max Activating Token Index: 939

Text #10

Max Range: 0.9013. Min Range: -0.9013

Max Act: 0.4198. Min Act: -0.0001

Data Index: 1170110 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 0.9013. Min Range: -0.9013

Max Act: 0.4614. Min Act: -0.0001

Data Index: 205029 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 0.9013. Min Range: -0.9013

Max Act: 0.4521. Min Act: -0.0000

Data Index: 1403076 (Python Code)

Max Activating Token Index: 27

Text #13

Max Range: 0.9013. Min Range: -0.9013

Max Act: 0.4491. Min Act: -0.0001

Data Index: 683536 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 0.9013. Min Range: -0.9013

Max Act: 0.4578. Min Act: -0.0001

Data Index: 1121846 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 0.9013. Min Range: -0.9013

Max Act: 0.4250. Min Act: -0.0001

Data Index: 57334 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 0.9013. Min Range: -0.9013

Max Act: 0.4117. Min Act: -0.0000

Data Index: 313617 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 0.9013. Min Range: -0.9013

Max Act: 0.4449. Min Act: -0.0001

Data Index: 543269 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 0.9013. Min Range: -0.9013

Max Act: 0.4115. Min Act: -0.0001

Data Index: 948595 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 0.9013. Min Range: -0.9013

Max Act: 0.4186. Min Act: -0.0001

Data Index: 1173182 (C4 (Web Text))

Max Activating Token Index: 143