Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2029 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.2705. Min Act: -0.0001

Data Index: 445326 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.2212. Min Act: -0.0001

Data Index: 1597423 (Python Code)

Max Activating Token Index: 104

Text #2

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.2293. Min Act: -0.0001

Data Index: 46541 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.2088. Min Act: -0.0001

Data Index: 838156 (C4 (Web Text))

Max Activating Token Index: 864

Text #4

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.2136. Min Act: -0.0001

Data Index: 1311099 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.1959. Min Act: -0.0001

Data Index: 827964 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.2153. Min Act: -0.0001

Data Index: 822190 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.2229. Min Act: -0.0001

Data Index: 734584 (C4 (Web Text))

Max Activating Token Index: 510

Text #8

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.2063. Min Act: -0.0001

Data Index: 830295 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.2051. Min Act: -0.0001

Data Index: 344506 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.2200. Min Act: -0.0001

Data Index: 964380 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.2226. Min Act: -0.0001

Data Index: 67986 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.2020. Min Act: -0.0001

Data Index: 592544 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.2081. Min Act: -0.0001

Data Index: 57634 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.1990. Min Act: -0.0001

Data Index: 628140 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.1936. Min Act: -0.0001

Data Index: 1571772 (Python Code)

Max Activating Token Index: 640

Text #16

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.1919. Min Act: -0.0001

Data Index: 1154324 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.2057. Min Act: -0.0001

Data Index: 186763 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.2129. Min Act: -0.0001

Data Index: 1236016 (C4 (Web Text))

Max Activating Token Index: 435

Text #19

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.2099. Min Act: -0.0001

Data Index: 713974 (C4 (Web Text))

Max Activating Token Index: 98