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

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

Neuron 3918 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: 0.8300. Min Range: -0.8300

Max Act: 0.8300. Min Act: -0.0000

Data Index: 784550 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 0.8300. Min Range: -0.8300

Max Act: 0.7228. Min Act: -0.0001

Data Index: 37130 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 0.8300. Min Range: -0.8300

Max Act: 0.6417. Min Act: -0.0001

Data Index: 236931 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 0.8300. Min Range: -0.8300

Max Act: 0.5927. Min Act: -0.0001

Data Index: 787645 (C4 (Web Text))

Max Activating Token Index: 754

Text #4

Max Range: 0.8300. Min Range: -0.8300

Max Act: 0.5969. Min Act: -0.0001

Data Index: 530213 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 0.8300. Min Range: -0.8300

Max Act: 0.5890. Min Act: -0.0000

Data Index: 340066 (C4 (Web Text))

Max Activating Token Index: 480

Text #6

Max Range: 0.8300. Min Range: -0.8300

Max Act: 0.5828. Min Act: -0.0000

Data Index: 838014 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 0.8300. Min Range: -0.8300

Max Act: 0.5470. Min Act: -0.0000

Data Index: 484583 (C4 (Web Text))

Max Activating Token Index: 777

Text #8

Max Range: 0.8300. Min Range: -0.8300

Max Act: 0.5608. Min Act: -0.0001

Data Index: 847348 (C4 (Web Text))

Max Activating Token Index: 182

Text #9

Max Range: 0.8300. Min Range: -0.8300

Max Act: 0.5299. Min Act: -0.0000

Data Index: 574664 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 0.8300. Min Range: -0.8300

Max Act: 0.5404. Min Act: -0.0000

Data Index: 541489 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 0.8300. Min Range: -0.8300

Max Act: 0.5319. Min Act: -0.0001

Data Index: 693526 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 0.8300. Min Range: -0.8300

Max Act: 0.5276. Min Act: -0.0000

Data Index: 947008 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 0.8300. Min Range: -0.8300

Max Act: 0.5267. Min Act: -0.0000

Data Index: 1349149 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 0.8300. Min Range: -0.8300

Max Act: 0.5120. Min Act: -0.0001

Data Index: 1303850 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 0.8300. Min Range: -0.8300

Max Act: 0.4834. Min Act: -0.0000

Data Index: 701831 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 0.8300. Min Range: -0.8300

Max Act: 0.4642. Min Act: -0.0000

Data Index: 153750 (C4 (Web Text))

Max Activating Token Index: 584

Text #17

Max Range: 0.8300. Min Range: -0.8300

Max Act: 0.4712. Min Act: -0.0000

Data Index: 225977 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 0.8300. Min Range: -0.8300

Max Act: 0.4622. Min Act: -0.0000

Data Index: 521421 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 0.8300. Min Range: -0.8300

Max Act: 0.4845. Min Act: -0.0000

Data Index: 286779 (C4 (Web Text))

Max Activating Token Index: 18