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

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

Neuron 3849 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.3425. Min Act: -0.0000

Data Index: 184142 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.3223. Min Act: -0.0000

Data Index: 97730 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.3040. Min Act: -0.0000

Data Index: 530858 (C4 (Web Text))

Max Activating Token Index: 899

Text #3

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.3148. Min Act: -0.0001

Data Index: 600082 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2843. Min Act: -0.0000

Data Index: 1014867 (C4 (Web Text))

Max Activating Token Index: 845

Text #5

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2964. Min Act: -0.0000

Data Index: 176575 (C4 (Web Text))

Max Activating Token Index: 866

Text #6

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2753. Min Act: -0.0000

Data Index: 91727 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2627. Min Act: -0.0001

Data Index: 557605 (C4 (Web Text))

Max Activating Token Index: 824

Text #8

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2607. Min Act: -0.0000

Data Index: 1079757 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2590. Min Act: -0.0000

Data Index: 395667 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2607. Min Act: -0.0001

Data Index: 1334108 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2423. Min Act: -0.0001

Data Index: 1178866 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2462. Min Act: -0.0001

Data Index: 530738 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2452. Min Act: -0.0000

Data Index: 1220221 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2524. Min Act: -0.0000

Data Index: 666875 (C4 (Web Text))

Max Activating Token Index: 998

Text #15

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2455. Min Act: -0.0000

Data Index: 1653992 (Python Code)

Max Activating Token Index: 993

Text #16

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2368. Min Act: -0.0000

Data Index: 1280784 (C4 (Web Text))

Max Activating Token Index: 433

Text #17

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2503. Min Act: -0.0001

Data Index: 912926 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2277. Min Act: -0.0001

Data Index: 892582 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2401. Min Act: -0.0000

Data Index: 103061 (C4 (Web Text))

Max Activating Token Index: 458