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

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

Neuron 5165 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0768. Min Act: -0.0002

Data Index: 426368 (C4 (Web Text))

Max Activating Token Index: 326

Text #1

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0658. Min Act: -0.0002

Data Index: 943821 (C4 (Web Text))

Max Activating Token Index: 489

Text #2

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0657. Min Act: -0.0002

Data Index: 365356 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0645. Min Act: -0.0002

Data Index: 960288 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0608. Min Act: -0.0002

Data Index: 268401 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0596. Min Act: -0.0002

Data Index: 669054 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0581. Min Act: -0.0002

Data Index: 193639 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0605. Min Act: -0.0002

Data Index: 751839 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0585. Min Act: -0.0002

Data Index: 529656 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0582. Min Act: -0.0002

Data Index: 294329 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0577. Min Act: -0.0002

Data Index: 142694 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0577. Min Act: -0.0002

Data Index: 575091 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0552. Min Act: -0.0002

Data Index: 626733 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0544. Min Act: -0.0002

Data Index: 145049 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0545. Min Act: -0.0002

Data Index: 853937 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0540. Min Act: -0.0002

Data Index: 385429 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0538. Min Act: -0.0002

Data Index: 742765 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0517. Min Act: -0.0002

Data Index: 418774 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0501. Min Act: -0.0002

Data Index: 422972 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0518. Min Act: -0.0002

Data Index: 517033 (C4 (Web Text))

Max Activating Token Index: 597