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

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

Neuron 2091 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0654. Min Act: -0.0001

Data Index: 1183511 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0697. Min Act: -0.0001

Data Index: 565096 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0655. Min Act: -0.0001

Data Index: 79440 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0551. Min Act: -0.0001

Data Index: 216867 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0540. Min Act: -0.0001

Data Index: 976140 (C4 (Web Text))

Max Activating Token Index: 612

Text #5

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0552. Min Act: -0.0001

Data Index: 804299 (C4 (Web Text))

Max Activating Token Index: 3

Text #6

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0546. Min Act: -0.0001

Data Index: 973633 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0512. Min Act: -0.0001

Data Index: 156907 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0476. Min Act: -0.0001

Data Index: 1237283 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0504. Min Act: -0.0001

Data Index: 960952 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0487. Min Act: -0.0001

Data Index: 1316051 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0524. Min Act: -0.0001

Data Index: 679555 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0417. Min Act: -0.0001

Data Index: 1331807 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0506. Min Act: -0.0001

Data Index: 140355 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0410. Min Act: -0.0001

Data Index: 213495 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0499. Min Act: -0.0001

Data Index: 9298 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0430. Min Act: -0.0001

Data Index: 209977 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0514. Min Act: -0.0001

Data Index: 111158 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0451. Min Act: -0.0001

Data Index: 763007 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0421. Min Act: -0.0001

Data Index: 387729 (C4 (Web Text))

Max Activating Token Index: 578