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

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

Neuron 130 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: 0.4722. Min Range: -0.4722

Max Act: 0.4722. Min Act: 0.0000

Data Index: 1023902 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4607. Min Act: -0.0000

Data Index: 984171 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4618. Min Act: -0.0000

Data Index: 118469 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4453. Min Act: -0.0000

Data Index: 1259254 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4487. Min Act: -0.0000

Data Index: 69186 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4441. Min Act: -0.0000

Data Index: 104697 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4440. Min Act: -0.0000

Data Index: 464028 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4316. Min Act: -0.0000

Data Index: 1028139 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4278. Min Act: -0.0000

Data Index: 912220 (C4 (Web Text))

Max Activating Token Index: 962

Text #9

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4313. Min Act: -0.0000

Data Index: 496259 (C4 (Web Text))

Max Activating Token Index: 865

Text #10

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4405. Min Act: -0.0000

Data Index: 251678 (C4 (Web Text))

Max Activating Token Index: 932

Text #11

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4060. Min Act: -0.0000

Data Index: 998089 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4140. Min Act: -0.0000

Data Index: 907133 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4111. Min Act: -0.0000

Data Index: 149672 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4271. Min Act: -0.0000

Data Index: 377987 (C4 (Web Text))

Max Activating Token Index: 625

Text #15

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.3957. Min Act: -0.0000

Data Index: 1099058 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4217. Min Act: -0.0000

Data Index: 439625 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.3938. Min Act: -0.0000

Data Index: 15469 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4006. Min Act: -0.0000

Data Index: 823015 (C4 (Web Text))

Max Activating Token Index: 555

Text #19

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.3813. Min Act: -0.0000

Data Index: 971141 (C4 (Web Text))

Max Activating Token Index: 288