Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1788 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.4743. Min Act: -0.0004

Data Index: 1325141 (C4 (Web Text))

Max Activating Token Index: 634

Text #1

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3543. Min Act: -0.0004

Data Index: 15366 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3128. Min Act: -0.0004

Data Index: 1162382 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3810. Min Act: -0.0004

Data Index: 208981 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3432. Min Act: -0.0004

Data Index: 1232852 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3437. Min Act: -0.0004

Data Index: 481163 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3857. Min Act: -0.0004

Data Index: 438072 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3546. Min Act: -0.0004

Data Index: 671320 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3386. Min Act: -0.0004

Data Index: 1117632 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3263. Min Act: -0.0004

Data Index: 1077511 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3102. Min Act: -0.0004

Data Index: 381125 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3134. Min Act: -0.0004

Data Index: 1017535 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3499. Min Act: -0.0004

Data Index: 690000 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3011. Min Act: -0.0004

Data Index: 309971 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.2666. Min Act: -0.0004

Data Index: 112245 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3148. Min Act: -0.0004

Data Index: 1046713 (C4 (Web Text))

Max Activating Token Index: 488

Text #16

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3238. Min Act: -0.0004

Data Index: 557278 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.2992. Min Act: -0.0004

Data Index: 811500 (C4 (Web Text))

Max Activating Token Index: 478

Text #18

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.2873. Min Act: -0.0004

Data Index: 1297113 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.2749. Min Act: -0.0004

Data Index: 955151 (C4 (Web Text))

Max Activating Token Index: 557