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

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

Neuron 4676 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7649. Min Range: -2.7649

Max Act: 2.7649. Min Act: 0.0000

Data Index: 957503 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 2.7649. Min Range: -2.7649

Max Act: 2.3909. Min Act: -0.0000

Data Index: 114098 (C4 (Web Text))

Max Activating Token Index: 374

Text #2

Max Range: 2.7649. Min Range: -2.7649

Max Act: 2.5183. Min Act: -0.0000

Data Index: 1007523 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 2.7649. Min Range: -2.7649

Max Act: 2.1933. Min Act: -0.0000

Data Index: 1311310 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 2.7649. Min Range: -2.7649

Max Act: 2.4388. Min Act: 0.0000

Data Index: 757484 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 2.7649. Min Range: -2.7649

Max Act: 2.2880. Min Act: -0.0000

Data Index: 486859 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 2.7649. Min Range: -2.7649

Max Act: 2.0454. Min Act: -0.0000

Data Index: 550938 (C4 (Web Text))

Max Activating Token Index: 419

Text #7

Max Range: 2.7649. Min Range: -2.7649

Max Act: 2.3415. Min Act: -0.0000

Data Index: 1276546 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 2.7649. Min Range: -2.7649

Max Act: 2.0072. Min Act: -0.0000

Data Index: 1297664 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 2.7649. Min Range: -2.7649

Max Act: 2.3366. Min Act: -0.0000

Data Index: 1195573 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 2.7649. Min Range: -2.7649

Max Act: 1.9585. Min Act: -0.0000

Data Index: 1083321 (C4 (Web Text))

Max Activating Token Index: 351

Text #11

Max Range: 2.7649. Min Range: -2.7649

Max Act: 1.9373. Min Act: 0.0000

Data Index: 685278 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 2.7649. Min Range: -2.7649

Max Act: 2.1632. Min Act: -0.0000

Data Index: 926447 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 2.7649. Min Range: -2.7649

Max Act: 1.9851. Min Act: -0.0000

Data Index: 533354 (C4 (Web Text))

Max Activating Token Index: 698

Text #14

Max Range: 2.7649. Min Range: -2.7649

Max Act: 2.0708. Min Act: 0.0000

Data Index: 485373 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 2.7649. Min Range: -2.7649

Max Act: 2.0613. Min Act: 0.0000

Data Index: 909606 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 2.7649. Min Range: -2.7649

Max Act: 1.9439. Min Act: 0.0000

Data Index: 881021 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 2.7649. Min Range: -2.7649

Max Act: 1.9224. Min Act: -0.0000

Data Index: 416742 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 2.7649. Min Range: -2.7649

Max Act: 1.8101. Min Act: -0.0000

Data Index: 1147683 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 2.7649. Min Range: -2.7649

Max Act: 1.8569. Min Act: -0.0000

Data Index: 721184 (C4 (Web Text))

Max Activating Token Index: 6