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

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

Neuron 4404 in Layer 1

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: 2.0946. Min Range: -2.0946

Max Act: 2.0946. Min Act: -0.0002

Data Index: 931828 (C4 (Web Text))

Max Activating Token Index: 832

Text #1

Max Range: 2.0946. Min Range: -2.0946

Max Act: 2.0895. Min Act: -0.0002

Data Index: 653485 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 2.0946. Min Range: -2.0946

Max Act: 2.0217. Min Act: -0.0002

Data Index: 1194019 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 2.0946. Min Range: -2.0946

Max Act: 2.0168. Min Act: -0.0002

Data Index: 950869 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 2.0946. Min Range: -2.0946

Max Act: 2.0245. Min Act: -0.0002

Data Index: 157965 (C4 (Web Text))

Max Activating Token Index: 306

Text #5

Max Range: 2.0946. Min Range: -2.0946

Max Act: 1.9864. Min Act: -0.0002

Data Index: 477050 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 2.0946. Min Range: -2.0946

Max Act: 1.9558. Min Act: -0.0002

Data Index: 418644 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 2.0946. Min Range: -2.0946

Max Act: 2.0110. Min Act: -0.0002

Data Index: 812756 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 2.0946. Min Range: -2.0946

Max Act: 1.9325. Min Act: -0.0002

Data Index: 172922 (C4 (Web Text))

Max Activating Token Index: 362

Text #9

Max Range: 2.0946. Min Range: -2.0946

Max Act: 1.9208. Min Act: -0.0002

Data Index: 1090222 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 2.0946. Min Range: -2.0946

Max Act: 1.9343. Min Act: -0.0002

Data Index: 1198474 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 2.0946. Min Range: -2.0946

Max Act: 1.9061. Min Act: -0.0002

Data Index: 275007 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 2.0946. Min Range: -2.0946

Max Act: 1.9083. Min Act: -0.0003

Data Index: 965237 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 2.0946. Min Range: -2.0946

Max Act: 1.9010. Min Act: -0.0002

Data Index: 1119093 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 2.0946. Min Range: -2.0946

Max Act: 1.8714. Min Act: -0.0003

Data Index: 731809 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 2.0946. Min Range: -2.0946

Max Act: 1.8963. Min Act: -0.0002

Data Index: 925607 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 2.0946. Min Range: -2.0946

Max Act: 1.8676. Min Act: -0.0002

Data Index: 84408 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 2.0946. Min Range: -2.0946

Max Act: 1.8665. Min Act: -0.0002

Data Index: 663971 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 2.0946. Min Range: -2.0946

Max Act: 1.8290. Min Act: -0.0002

Data Index: 1344097 (C4 (Web Text))

Max Activating Token Index: 133

Text #19

Max Range: 2.0946. Min Range: -2.0946

Max Act: 1.8234. Min Act: -0.0002

Data Index: 77627 (C4 (Web Text))

Max Activating Token Index: 126