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

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

Neuron 1126 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: 0.0501. Min Range: -0.0501

Max Act: 0.0501. Min Act: -0.0000

Data Index: 1231158 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0433. Min Act: -0.0001

Data Index: 460693 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0395. Min Act: -0.0001

Data Index: 376050 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0363. Min Act: -0.0000

Data Index: 239882 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0390. Min Act: -0.0000

Data Index: 506384 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0384. Min Act: -0.0001

Data Index: 1007494 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0386. Min Act: -0.0001

Data Index: 905021 (C4 (Web Text))

Max Activating Token Index: 649

Text #7

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0370. Min Act: -0.0001

Data Index: 659602 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0351. Min Act: -0.0000

Data Index: 1332403 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0347. Min Act: -0.0000

Data Index: 127064 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0387. Min Act: -0.0000

Data Index: 875417 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0347. Min Act: -0.0000

Data Index: 1324825 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0342. Min Act: -0.0000

Data Index: 984278 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0361. Min Act: -0.0001

Data Index: 564732 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0333. Min Act: -0.0000

Data Index: 1303853 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0323. Min Act: -0.0001

Data Index: 727897 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0325. Min Act: -0.0001

Data Index: 189320 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0325. Min Act: -0.0000

Data Index: 1147561 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0310. Min Act: -0.0000

Data Index: 106613 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0323. Min Act: -0.0001

Data Index: 771931 (C4 (Web Text))

Max Activating Token Index: 346