Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1554 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.3670. Min Act: -0.0000

Data Index: 1122273 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.3306. Min Act: -0.0000

Data Index: 493778 (C4 (Web Text))

Max Activating Token Index: 369

Text #2

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.3591. Min Act: -0.0000

Data Index: 1316128 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.3279. Min Act: -0.0000

Data Index: 474444 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.3239. Min Act: -0.0000

Data Index: 1132007 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2932. Min Act: -0.0000

Data Index: 1114328 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.3146. Min Act: -0.0000

Data Index: 1131905 (C4 (Web Text))

Max Activating Token Index: 959

Text #7

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.3092. Min Act: -0.0000

Data Index: 1042012 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2719. Min Act: -0.0000

Data Index: 1122521 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2914. Min Act: -0.0000

Data Index: 1278271 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.3155. Min Act: -0.0000

Data Index: 26127 (C4 (Web Text))

Max Activating Token Index: 914

Text #11

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2943. Min Act: -0.0000

Data Index: 1068384 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2900. Min Act: -0.0000

Data Index: 1263614 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2651. Min Act: -0.0000

Data Index: 771081 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2884. Min Act: -0.0000

Data Index: 117904 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2735. Min Act: -0.0000

Data Index: 1041105 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2628. Min Act: -0.0000

Data Index: 1074463 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2587. Min Act: -0.0000

Data Index: 814859 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2682. Min Act: -0.0000

Data Index: 1172038 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2459. Min Act: -0.0000

Data Index: 1623050 (Python Code)

Max Activating Token Index: 198