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

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

Neuron 3024 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: 4.2007. Min Range: -4.2007

Max Act: 4.2007. Min Act: -0.0001

Data Index: 563220 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 4.2007. Min Range: -4.2007

Max Act: 4.0350. Min Act: -0.0001

Data Index: 1316647 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 4.2007. Min Range: -4.2007

Max Act: 3.4490. Min Act: -0.0001

Data Index: 98027 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 4.2007. Min Range: -4.2007

Max Act: 3.5068. Min Act: -0.0000

Data Index: 478498 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 4.2007. Min Range: -4.2007

Max Act: 3.3578. Min Act: -0.0000

Data Index: 896096 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 4.2007. Min Range: -4.2007

Max Act: 3.0957. Min Act: -0.0001

Data Index: 1124717 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 4.2007. Min Range: -4.2007

Max Act: 3.3606. Min Act: -0.0000

Data Index: 713585 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 4.2007. Min Range: -4.2007

Max Act: 3.2052. Min Act: -0.0001

Data Index: 1173352 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 4.2007. Min Range: -4.2007

Max Act: 3.2803. Min Act: -0.0000

Data Index: 1192595 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 4.2007. Min Range: -4.2007

Max Act: 3.0302. Min Act: -0.0000

Data Index: 65843 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 4.2007. Min Range: -4.2007

Max Act: 3.0145. Min Act: -0.0000

Data Index: 33753 (C4 (Web Text))

Max Activating Token Index: 771

Text #11

Max Range: 4.2007. Min Range: -4.2007

Max Act: 2.8534. Min Act: -0.0000

Data Index: 881922 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 4.2007. Min Range: -4.2007

Max Act: 2.8449. Min Act: -0.0001

Data Index: 738293 (C4 (Web Text))

Max Activating Token Index: 1008

Text #13

Max Range: 4.2007. Min Range: -4.2007

Max Act: 2.9623. Min Act: -0.0001

Data Index: 437017 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 4.2007. Min Range: -4.2007

Max Act: 3.0781. Min Act: -0.0001

Data Index: 967261 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 4.2007. Min Range: -4.2007

Max Act: 2.9347. Min Act: -0.0000

Data Index: 47588 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 4.2007. Min Range: -4.2007

Max Act: 2.7752. Min Act: -0.0000

Data Index: 589021 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 4.2007. Min Range: -4.2007

Max Act: 3.0205. Min Act: -0.0001

Data Index: 462535 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 4.2007. Min Range: -4.2007

Max Act: 2.9779. Min Act: -0.0000

Data Index: 429778 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 4.2007. Min Range: -4.2007

Max Act: 2.9789. Min Act: -0.0000

Data Index: 1267335 (C4 (Web Text))

Max Activating Token Index: 531