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

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

Neuron 2615 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0687. Min Act: -0.0000

Data Index: 1520298 (Python Code)

Max Activating Token Index: 895

Text #1

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0615. Min Act: -0.0001

Data Index: 1500742 (Python Code)

Max Activating Token Index: 987

Text #2

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0575. Min Act: -0.0001

Data Index: 278036 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0544. Min Act: -0.0001

Data Index: 136728 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0467. Min Act: -0.0001

Data Index: 1352609 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0515. Min Act: -0.0001

Data Index: 1154979 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0495. Min Act: -0.0001

Data Index: 236170 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0522. Min Act: -0.0001

Data Index: 102174 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0468. Min Act: -0.0001

Data Index: 330858 (C4 (Web Text))

Max Activating Token Index: 418

Text #9

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0466. Min Act: -0.0001

Data Index: 1095423 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0479. Min Act: -0.0000

Data Index: 559563 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0488. Min Act: -0.0001

Data Index: 964239 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0457. Min Act: -0.0001

Data Index: 210878 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0432. Min Act: -0.0001

Data Index: 570059 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0467. Min Act: -0.0001

Data Index: 520383 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0477. Min Act: -0.0000

Data Index: 1440744 (Python Code)

Max Activating Token Index: 448

Text #16

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0454. Min Act: -0.0001

Data Index: 262488 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0461. Min Act: -0.0001

Data Index: 596157 (C4 (Web Text))

Max Activating Token Index: 588

Text #18

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0455. Min Act: -0.0001

Data Index: 136314 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0422. Min Act: -0.0001

Data Index: 869357 (C4 (Web Text))

Max Activating Token Index: 421