Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5101 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.5462. Min Act: -0.0000

Data Index: 871991 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.5722. Min Act: -0.0000

Data Index: 316111 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4893. Min Act: -0.0000

Data Index: 298681 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.5305. Min Act: -0.0000

Data Index: 523214 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4905. Min Act: -0.0000

Data Index: 363136 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4210. Min Act: -0.0000

Data Index: 1345025 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4402. Min Act: -0.0000

Data Index: 125952 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4995. Min Act: -0.0000

Data Index: 1149278 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4844. Min Act: -0.0000

Data Index: 250144 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4228. Min Act: -0.0000

Data Index: 1294692 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4296. Min Act: -0.0000

Data Index: 1084517 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4173. Min Act: -0.0000

Data Index: 449590 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4253. Min Act: -0.0000

Data Index: 73182 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.3480. Min Act: -0.0000

Data Index: 911850 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4452. Min Act: -0.0000

Data Index: 1203853 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4054. Min Act: -0.0000

Data Index: 734019 (C4 (Web Text))

Max Activating Token Index: 523

Text #16

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4289. Min Act: -0.0000

Data Index: 728747 (C4 (Web Text))

Max Activating Token Index: 362

Text #17

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4250. Min Act: -0.0000

Data Index: 1055696 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.3717. Min Act: -0.0000

Data Index: 501141 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4201. Min Act: -0.0000

Data Index: 596216 (C4 (Web Text))

Max Activating Token Index: 184