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

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

Neuron 4372 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.7671. Min Range: -1.7671

Max Act: 1.7395. Min Act: -0.0002

Data Index: 165770 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 1.7671. Min Range: -1.7671

Max Act: 1.6956. Min Act: -0.0002

Data Index: 1007157 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 1.7671. Min Range: -1.7671

Max Act: 1.7671. Min Act: -0.0002

Data Index: 1064440 (C4 (Web Text))

Max Activating Token Index: 856

Text #3

Max Range: 1.7671. Min Range: -1.7671

Max Act: 1.6761. Min Act: -0.0001

Data Index: 1164715 (C4 (Web Text))

Max Activating Token Index: 410

Text #4

Max Range: 1.7671. Min Range: -1.7671

Max Act: 1.6583. Min Act: -0.0002

Data Index: 482107 (C4 (Web Text))

Max Activating Token Index: 439

Text #5

Max Range: 1.7671. Min Range: -1.7671

Max Act: 1.6723. Min Act: -0.0002

Data Index: 1211578 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 1.7671. Min Range: -1.7671

Max Act: 1.6197. Min Act: -0.0002

Data Index: 433718 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 1.7671. Min Range: -1.7671

Max Act: 1.6670. Min Act: -0.0002

Data Index: 1251659 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 1.7671. Min Range: -1.7671

Max Act: 1.6051. Min Act: -0.0002

Data Index: 354265 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 1.7671. Min Range: -1.7671

Max Act: 1.6308. Min Act: -0.0002

Data Index: 415280 (C4 (Web Text))

Max Activating Token Index: 344

Text #10

Max Range: 1.7671. Min Range: -1.7671

Max Act: 1.5975. Min Act: -0.0002

Data Index: 119182 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 1.7671. Min Range: -1.7671

Max Act: 1.5592. Min Act: -0.0002

Data Index: 137182 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 1.7671. Min Range: -1.7671

Max Act: 1.5325. Min Act: -0.0002

Data Index: 648517 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 1.7671. Min Range: -1.7671

Max Act: 1.6027. Min Act: -0.0002

Data Index: 570738 (C4 (Web Text))

Max Activating Token Index: 826

Text #14

Max Range: 1.7671. Min Range: -1.7671

Max Act: 1.5782. Min Act: -0.0002

Data Index: 583796 (C4 (Web Text))

Max Activating Token Index: 413

Text #15

Max Range: 1.7671. Min Range: -1.7671

Max Act: 1.5389. Min Act: -0.0002

Data Index: 910588 (C4 (Web Text))

Max Activating Token Index: 737

Text #16

Max Range: 1.7671. Min Range: -1.7671

Max Act: 1.5385. Min Act: -0.0002

Data Index: 412602 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 1.7671. Min Range: -1.7671

Max Act: 1.5671. Min Act: -0.0002

Data Index: 953112 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 1.7671. Min Range: -1.7671

Max Act: 1.5805. Min Act: -0.0002

Data Index: 635171 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 1.7671. Min Range: -1.7671

Max Act: 1.5053. Min Act: -0.0002

Data Index: 935608 (C4 (Web Text))

Max Activating Token Index: 703