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

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

Neuron 3310 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: 5.5823. Min Range: -5.5823

Max Act: 5.5823. Min Act: -0.0001

Data Index: 201446 (C4 (Web Text))

Max Activating Token Index: 302

Text #1

Max Range: 5.5823. Min Range: -5.5823

Max Act: 4.3158. Min Act: -0.0000

Data Index: 373838 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 5.5823. Min Range: -5.5823

Max Act: 4.1482. Min Act: -0.0001

Data Index: 1029873 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 5.5823. Min Range: -5.5823

Max Act: 4.3054. Min Act: -0.0001

Data Index: 1352114 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 5.5823. Min Range: -5.5823

Max Act: 4.4246. Min Act: -0.0001

Data Index: 4070 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 5.5823. Min Range: -5.5823

Max Act: 4.0063. Min Act: -0.0001

Data Index: 644652 (C4 (Web Text))

Max Activating Token Index: 419

Text #6

Max Range: 5.5823. Min Range: -5.5823

Max Act: 4.1136. Min Act: -0.0000

Data Index: 293871 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 5.5823. Min Range: -5.5823

Max Act: 3.9816. Min Act: -0.0000

Data Index: 1254171 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 5.5823. Min Range: -5.5823

Max Act: 3.8452. Min Act: -0.0001

Data Index: 838003 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 5.5823. Min Range: -5.5823

Max Act: 3.8535. Min Act: -0.0001

Data Index: 541440 (C4 (Web Text))

Max Activating Token Index: 709

Text #10

Max Range: 5.5823. Min Range: -5.5823

Max Act: 3.6301. Min Act: -0.0000

Data Index: 339790 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 5.5823. Min Range: -5.5823

Max Act: 3.5593. Min Act: -0.0000

Data Index: 516942 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 5.5823. Min Range: -5.5823

Max Act: 3.9952. Min Act: -0.0000

Data Index: 936629 (C4 (Web Text))

Max Activating Token Index: 379

Text #13

Max Range: 5.5823. Min Range: -5.5823

Max Act: 3.6513. Min Act: -0.0000

Data Index: 506052 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 5.5823. Min Range: -5.5823

Max Act: 3.6306. Min Act: -0.0000

Data Index: 457256 (C4 (Web Text))

Max Activating Token Index: 691

Text #15

Max Range: 5.5823. Min Range: -5.5823

Max Act: 3.5969. Min Act: -0.0000

Data Index: 318199 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 5.5823. Min Range: -5.5823

Max Act: 3.5486. Min Act: -0.0000

Data Index: 817201 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 5.5823. Min Range: -5.5823

Max Act: 3.5468. Min Act: -0.0001

Data Index: 247478 (C4 (Web Text))

Max Activating Token Index: 522

Text #18

Max Range: 5.5823. Min Range: -5.5823

Max Act: 3.4713. Min Act: -0.0001

Data Index: 308803 (C4 (Web Text))

Max Activating Token Index: 81

Text #19

Max Range: 5.5823. Min Range: -5.5823

Max Act: 3.1612. Min Act: -0.0000

Data Index: 620107 (C4 (Web Text))

Max Activating Token Index: 325