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

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

Neuron 4658 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.4349. Min Act: -0.0000

Data Index: 925796 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.4056. Min Act: -0.0000

Data Index: 1470434 (Python Code)

Max Activating Token Index: 1015

Text #2

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.4037. Min Act: -0.0000

Data Index: 1267763 (C4 (Web Text))

Max Activating Token Index: 665

Text #3

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3680. Min Act: -0.0000

Data Index: 1511598 (Python Code)

Max Activating Token Index: 624

Text #4

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.4088. Min Act: -0.0000

Data Index: 1645639 (Python Code)

Max Activating Token Index: 210

Text #5

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3501. Min Act: -0.0000

Data Index: 1545835 (Python Code)

Max Activating Token Index: 915

Text #6

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3518. Min Act: 0.0000

Data Index: 101839 (C4 (Web Text))

Max Activating Token Index: 671

Text #7

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3197. Min Act: -0.0000

Data Index: 486134 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3351. Min Act: -0.0000

Data Index: 1003401 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3327. Min Act: -0.0000

Data Index: 145625 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3116. Min Act: -0.0000

Data Index: 1409914 (Python Code)

Max Activating Token Index: 979

Text #11

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2949. Min Act: -0.0000

Data Index: 1522115 (Python Code)

Max Activating Token Index: 433

Text #12

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3464. Min Act: -0.0000

Data Index: 1285942 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3134. Min Act: 0.0000

Data Index: 397877 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3045. Min Act: -0.0000

Data Index: 1451456 (Python Code)

Max Activating Token Index: 412

Text #15

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3099. Min Act: -0.0000

Data Index: 325969 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3221. Min Act: -0.0000

Data Index: 751046 (C4 (Web Text))

Max Activating Token Index: 441

Text #17

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3080. Min Act: -0.0000

Data Index: 1312495 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3149. Min Act: -0.0000

Data Index: 1204489 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2989. Min Act: -0.0000

Data Index: 940545 (C4 (Web Text))

Max Activating Token Index: 523