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

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

Neuron 4096 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.4004. Min Act: -0.0000

Data Index: 222219 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.3802. Min Act: -0.0000

Data Index: 620629 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.3762. Min Act: -0.0000

Data Index: 963890 (C4 (Web Text))

Max Activating Token Index: 802

Text #3

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.3489. Min Act: -0.0000

Data Index: 650141 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.3158. Min Act: -0.0000

Data Index: 165822 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.3122. Min Act: -0.0000

Data Index: 353075 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.2835. Min Act: -0.0000

Data Index: 1055467 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.3359. Min Act: -0.0000

Data Index: 902565 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.3196. Min Act: -0.0000

Data Index: 692474 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.2954. Min Act: -0.0000

Data Index: 238721 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.3138. Min Act: -0.0000

Data Index: 1022287 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.2610. Min Act: -0.0000

Data Index: 301357 (C4 (Web Text))

Max Activating Token Index: 177

Text #12

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.2796. Min Act: -0.0000

Data Index: 484500 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.2957. Min Act: -0.0000

Data Index: 66055 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.2948. Min Act: -0.0000

Data Index: 229470 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.2737. Min Act: -0.0000

Data Index: 1212705 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.2910. Min Act: -0.0000

Data Index: 1065219 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.2874. Min Act: -0.0000

Data Index: 536203 (C4 (Web Text))

Max Activating Token Index: 875

Text #18

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.2563. Min Act: -0.0000

Data Index: 844098 (C4 (Web Text))

Max Activating Token Index: 412

Text #19

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.2734. Min Act: -0.0000

Data Index: 1348359 (C4 (Web Text))

Max Activating Token Index: 599