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

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

Neuron 1562 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2708. Min Range: -1.2708

Max Act: 1.2708. Min Act: -0.0001

Data Index: 344158 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 1.2708. Min Range: -1.2708

Max Act: 1.1932. Min Act: -0.0001

Data Index: 824666 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 1.2708. Min Range: -1.2708

Max Act: 1.0991. Min Act: -0.0001

Data Index: 174933 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 1.2708. Min Range: -1.2708

Max Act: 1.1502. Min Act: -0.0001

Data Index: 1136000 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 1.2708. Min Range: -1.2708

Max Act: 1.1864. Min Act: -0.0001

Data Index: 357321 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 1.2708. Min Range: -1.2708

Max Act: 1.0882. Min Act: -0.0001

Data Index: 639293 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 1.2708. Min Range: -1.2708

Max Act: 1.1753. Min Act: -0.0001

Data Index: 967058 (C4 (Web Text))

Max Activating Token Index: 298

Text #7

Max Range: 1.2708. Min Range: -1.2708

Max Act: 1.1269. Min Act: -0.0001

Data Index: 823978 (C4 (Web Text))

Max Activating Token Index: 473

Text #8

Max Range: 1.2708. Min Range: -1.2708

Max Act: 1.1862. Min Act: -0.0001

Data Index: 1224694 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 1.2708. Min Range: -1.2708

Max Act: 1.0928. Min Act: -0.0001

Data Index: 444544 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 1.2708. Min Range: -1.2708

Max Act: 1.1543. Min Act: -0.0001

Data Index: 1015602 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 1.2708. Min Range: -1.2708

Max Act: 1.0772. Min Act: -0.0001

Data Index: 903339 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 1.2708. Min Range: -1.2708

Max Act: 1.1517. Min Act: -0.0001

Data Index: 131740 (C4 (Web Text))

Max Activating Token Index: 184

Text #13

Max Range: 1.2708. Min Range: -1.2708

Max Act: 1.0884. Min Act: -0.0001

Data Index: 79746 (C4 (Web Text))

Max Activating Token Index: 895

Text #14

Max Range: 1.2708. Min Range: -1.2708

Max Act: 1.1082. Min Act: -0.0001

Data Index: 205210 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 1.2708. Min Range: -1.2708

Max Act: 1.1005. Min Act: -0.0001

Data Index: 1169774 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 1.2708. Min Range: -1.2708

Max Act: 1.0961. Min Act: -0.0001

Data Index: 235090 (C4 (Web Text))

Max Activating Token Index: 441

Text #17

Max Range: 1.2708. Min Range: -1.2708

Max Act: 1.1017. Min Act: -0.0001

Data Index: 596198 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 1.2708. Min Range: -1.2708

Max Act: 1.0170. Min Act: -0.0001

Data Index: 136190 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 1.2708. Min Range: -1.2708

Max Act: 1.0874. Min Act: -0.0001

Data Index: 148204 (C4 (Web Text))

Max Activating Token Index: 143