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

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

Neuron 2374 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7775. Min Range: -1.7775

Max Act: 1.7775. Min Act: -0.0000

Data Index: 814518 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 1.7775. Min Range: -1.7775

Max Act: 1.6323. Min Act: -0.0000

Data Index: 1318301 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 1.7775. Min Range: -1.7775

Max Act: 1.5505. Min Act: -0.0001

Data Index: 591289 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 1.7775. Min Range: -1.7775

Max Act: 1.4856. Min Act: -0.0000

Data Index: 985696 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 1.7775. Min Range: -1.7775

Max Act: 1.4901. Min Act: -0.0001

Data Index: 1022228 (C4 (Web Text))

Max Activating Token Index: 661

Text #5

Max Range: 1.7775. Min Range: -1.7775

Max Act: 1.4236. Min Act: -0.0000

Data Index: 1081404 (C4 (Web Text))

Max Activating Token Index: 361

Text #6

Max Range: 1.7775. Min Range: -1.7775

Max Act: 1.1938. Min Act: -0.0000

Data Index: 1151882 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 1.7775. Min Range: -1.7775

Max Act: 1.2735. Min Act: -0.0001

Data Index: 310149 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 1.7775. Min Range: -1.7775

Max Act: 1.2594. Min Act: -0.0001

Data Index: 884577 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 1.7775. Min Range: -1.7775

Max Act: 1.1924. Min Act: -0.0000

Data Index: 816114 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 1.7775. Min Range: -1.7775

Max Act: 1.2641. Min Act: -0.0001

Data Index: 637893 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 1.7775. Min Range: -1.7775

Max Act: 1.4150. Min Act: -0.0001

Data Index: 1041251 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 1.7775. Min Range: -1.7775

Max Act: 1.2411. Min Act: -0.0001

Data Index: 1141575 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 1.7775. Min Range: -1.7775

Max Act: 1.1603. Min Act: -0.0000

Data Index: 951222 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 1.7775. Min Range: -1.7775

Max Act: 1.2074. Min Act: -0.0000

Data Index: 1193578 (C4 (Web Text))

Max Activating Token Index: 440

Text #15

Max Range: 1.7775. Min Range: -1.7775

Max Act: 1.2027. Min Act: -0.0000

Data Index: 703201 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 1.7775. Min Range: -1.7775

Max Act: 1.2016. Min Act: -0.0000

Data Index: 182866 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 1.7775. Min Range: -1.7775

Max Act: 1.1540. Min Act: -0.0000

Data Index: 1144308 (C4 (Web Text))

Max Activating Token Index: 474

Text #18

Max Range: 1.7775. Min Range: -1.7775

Max Act: 1.1870. Min Act: -0.0000

Data Index: 1231104 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 1.7775. Min Range: -1.7775

Max Act: 1.1672. Min Act: -0.0001

Data Index: 437383 (C4 (Web Text))

Max Activating Token Index: 983