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

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

Neuron 2918 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5993. Min Range: -1.5993

Max Act: 1.4967. Min Act: -0.0000

Data Index: 892746 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 1.5993. Min Range: -1.5993

Max Act: 1.5225. Min Act: -0.0000

Data Index: 675518 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 1.5993. Min Range: -1.5993

Max Act: 1.5993. Min Act: -0.0000

Data Index: 336236 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 1.5993. Min Range: -1.5993

Max Act: 1.3989. Min Act: -0.0000

Data Index: 883654 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 1.5993. Min Range: -1.5993

Max Act: 1.3902. Min Act: -0.0000

Data Index: 349376 (C4 (Web Text))

Max Activating Token Index: 447

Text #5

Max Range: 1.5993. Min Range: -1.5993

Max Act: 1.3145. Min Act: -0.0000

Data Index: 43705 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 1.5993. Min Range: -1.5993

Max Act: 1.3543. Min Act: -0.0000

Data Index: 865472 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 1.5993. Min Range: -1.5993

Max Act: 1.3206. Min Act: -0.0000

Data Index: 571317 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 1.5993. Min Range: -1.5993

Max Act: 1.2822. Min Act: -0.0000

Data Index: 5774 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 1.5993. Min Range: -1.5993

Max Act: 1.2058. Min Act: -0.0000

Data Index: 568392 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 1.5993. Min Range: -1.5993

Max Act: 1.2101. Min Act: -0.0000

Data Index: 337657 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 1.5993. Min Range: -1.5993

Max Act: 1.2100. Min Act: -0.0000

Data Index: 1611262 (Python Code)

Max Activating Token Index: 267

Text #12

Max Range: 1.5993. Min Range: -1.5993

Max Act: 1.2457. Min Act: -0.0000

Data Index: 620596 (C4 (Web Text))

Max Activating Token Index: 692

Text #13

Max Range: 1.5993. Min Range: -1.5993

Max Act: 1.3241. Min Act: -0.0000

Data Index: 90495 (C4 (Web Text))

Max Activating Token Index: 520

Text #14

Max Range: 1.5993. Min Range: -1.5993

Max Act: 1.2346. Min Act: -0.0000

Data Index: 947583 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 1.5993. Min Range: -1.5993

Max Act: 1.2827. Min Act: -0.0000

Data Index: 651256 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 1.5993. Min Range: -1.5993

Max Act: 1.1814. Min Act: -0.0000

Data Index: 469014 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 1.5993. Min Range: -1.5993

Max Act: 1.2210. Min Act: -0.0000

Data Index: 491066 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 1.5993. Min Range: -1.5993

Max Act: 1.1793. Min Act: -0.0000

Data Index: 218633 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 1.5993. Min Range: -1.5993

Max Act: 1.2524. Min Act: -0.0000

Data Index: 592178 (C4 (Web Text))

Max Activating Token Index: 429