Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2014 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.3698. Min Act: -0.0000

Data Index: 615045 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.4337. Min Act: -0.0000

Data Index: 296563 (C4 (Web Text))

Max Activating Token Index: 763

Text #2

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.5155. Min Act: -0.0000

Data Index: 711040 (C4 (Web Text))

Max Activating Token Index: 540

Text #3

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.5821. Min Act: -0.0000

Data Index: 1197252 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.3634. Min Act: -0.0000

Data Index: 270745 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.4192. Min Act: -0.0000

Data Index: 529683 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.3990. Min Act: -0.0000

Data Index: 380597 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.4414. Min Act: -0.0000

Data Index: 458858 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.3375. Min Act: -0.0000

Data Index: 316371 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.3384. Min Act: -0.0000

Data Index: 1020856 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.3326. Min Act: -0.0000

Data Index: 965000 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.2591. Min Act: -0.0000

Data Index: 1289023 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.3420. Min Act: -0.0000

Data Index: 497605 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.2498. Min Act: -0.0000

Data Index: 615127 (C4 (Web Text))

Max Activating Token Index: 97

Text #14

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.2755. Min Act: -0.0000

Data Index: 660664 (C4 (Web Text))

Max Activating Token Index: 264

Text #15

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.2485. Min Act: -0.0000

Data Index: 379546 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.2277. Min Act: -0.0000

Data Index: 480453 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.2723. Min Act: -0.0000

Data Index: 11338 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.3316. Min Act: -0.0000

Data Index: 660604 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.2597. Min Act: -0.0000

Data Index: 574481 (C4 (Web Text))

Max Activating Token Index: 905