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

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

Neuron 1535 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0668. Min Act: -0.0003

Data Index: 176065 (C4 (Web Text))

Max Activating Token Index: 777

Text #1

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0611. Min Act: -0.0003

Data Index: 205495 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0523. Min Act: -0.0003

Data Index: 573979 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0527. Min Act: -0.0003

Data Index: 483989 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0562. Min Act: -0.0003

Data Index: 445579 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0496. Min Act: -0.0003

Data Index: 252225 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0416. Min Act: -0.0003

Data Index: 1022824 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0501. Min Act: -0.0003

Data Index: 191852 (C4 (Web Text))

Max Activating Token Index: 674

Text #8

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0495. Min Act: -0.0003

Data Index: 417857 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0472. Min Act: -0.0003

Data Index: 452188 (C4 (Web Text))

Max Activating Token Index: 954

Text #10

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0492. Min Act: -0.0003

Data Index: 286181 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0453. Min Act: -0.0003

Data Index: 731004 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0451. Min Act: -0.0003

Data Index: 621994 (C4 (Web Text))

Max Activating Token Index: 861

Text #13

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0469. Min Act: -0.0003

Data Index: 855638 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0483. Min Act: -0.0003

Data Index: 38020 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0470. Min Act: -0.0003

Data Index: 709400 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0463. Min Act: -0.0003

Data Index: 1305633 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0437. Min Act: -0.0003

Data Index: 844242 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0444. Min Act: -0.0003

Data Index: 257938 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0461. Min Act: -0.0003

Data Index: 7075 (C4 (Web Text))

Max Activating Token Index: 800