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

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

Neuron 1742 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.8454. Min Range: -2.8454

Max Act: 2.8454. Min Act: -0.0002

Data Index: 1189618 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 2.8454. Min Range: -2.8454

Max Act: 2.4695. Min Act: -0.0003

Data Index: 29875 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 2.8454. Min Range: -2.8454

Max Act: 2.5538. Min Act: -0.0002

Data Index: 300892 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 2.8454. Min Range: -2.8454

Max Act: 2.5109. Min Act: -0.0002

Data Index: 540391 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 2.8454. Min Range: -2.8454

Max Act: 2.4699. Min Act: -0.0002

Data Index: 43383 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 2.8454. Min Range: -2.8454

Max Act: 2.4043. Min Act: -0.0002

Data Index: 23719 (C4 (Web Text))

Max Activating Token Index: 478

Text #6

Max Range: 2.8454. Min Range: -2.8454

Max Act: 2.3857. Min Act: -0.0002

Data Index: 737926 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 2.8454. Min Range: -2.8454

Max Act: 2.3506. Min Act: -0.0003

Data Index: 414181 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 2.8454. Min Range: -2.8454

Max Act: 2.2955. Min Act: -0.0002

Data Index: 1033164 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 2.8454. Min Range: -2.8454

Max Act: 2.2942. Min Act: -0.0002

Data Index: 1323204 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 2.8454. Min Range: -2.8454

Max Act: 2.2003. Min Act: -0.0002

Data Index: 878379 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 2.8454. Min Range: -2.8454

Max Act: 2.2143. Min Act: -0.0003

Data Index: 1033152 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 2.8454. Min Range: -2.8454

Max Act: 2.1971. Min Act: -0.0002

Data Index: 1201759 (C4 (Web Text))

Max Activating Token Index: 823

Text #13

Max Range: 2.8454. Min Range: -2.8454

Max Act: 2.1960. Min Act: -0.0002

Data Index: 722025 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 2.8454. Min Range: -2.8454

Max Act: 2.1542. Min Act: -0.0002

Data Index: 409739 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 2.8454. Min Range: -2.8454

Max Act: 2.1943. Min Act: -0.0002

Data Index: 348375 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 2.8454. Min Range: -2.8454

Max Act: 2.1950. Min Act: -0.0002

Data Index: 946680 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 2.8454. Min Range: -2.8454

Max Act: 2.1605. Min Act: -0.0002

Data Index: 1169617 (C4 (Web Text))

Max Activating Token Index: 483

Text #18

Max Range: 2.8454. Min Range: -2.8454

Max Act: 2.1543. Min Act: -0.0002

Data Index: 428065 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 2.8454. Min Range: -2.8454

Max Act: 2.1312. Min Act: -0.0002

Data Index: 1006247 (C4 (Web Text))

Max Activating Token Index: 292