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

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

Neuron 3435 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0583. Min Act: -0.0002

Data Index: 1002138 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0537. Min Act: -0.0002

Data Index: 3334 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0516. Min Act: -0.0002

Data Index: 204347 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0496. Min Act: -0.0002

Data Index: 785147 (C4 (Web Text))

Max Activating Token Index: 669

Text #4

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0494. Min Act: -0.0002

Data Index: 131901 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0495. Min Act: -0.0002

Data Index: 547754 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0473. Min Act: -0.0002

Data Index: 913433 (C4 (Web Text))

Max Activating Token Index: 468

Text #7

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0482. Min Act: -0.0002

Data Index: 400003 (C4 (Web Text))

Max Activating Token Index: 950

Text #8

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0446. Min Act: -0.0002

Data Index: 693037 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0522. Min Act: -0.0002

Data Index: 71234 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0487. Min Act: -0.0002

Data Index: 542401 (C4 (Web Text))

Max Activating Token Index: 792

Text #11

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0452. Min Act: -0.0002

Data Index: 997990 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0430. Min Act: -0.0002

Data Index: 948133 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0445. Min Act: -0.0002

Data Index: 534502 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0459. Min Act: -0.0002

Data Index: 269376 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0459. Min Act: -0.0002

Data Index: 970727 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0452. Min Act: -0.0002

Data Index: 932930 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0462. Min Act: -0.0002

Data Index: 699046 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0455. Min Act: -0.0002

Data Index: 1617424 (Python Code)

Max Activating Token Index: 488

Text #19

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0437. Min Act: -0.0002

Data Index: 500432 (C4 (Web Text))

Max Activating Token Index: 523