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

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

Neuron 3230 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3585. Min Range: -3.3585

Max Act: 3.3140. Min Act: -0.0000

Data Index: 359814 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 3.3585. Min Range: -3.3585

Max Act: 3.3585. Min Act: -0.0000

Data Index: 1282012 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 3.3585. Min Range: -3.3585

Max Act: 2.8728. Min Act: -0.0000

Data Index: 444157 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 3.3585. Min Range: -3.3585

Max Act: 3.0971. Min Act: -0.0000

Data Index: 879714 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 3.3585. Min Range: -3.3585

Max Act: 3.0022. Min Act: -0.0000

Data Index: 1066693 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 3.3585. Min Range: -3.3585

Max Act: 2.9635. Min Act: -0.0000

Data Index: 428222 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 3.3585. Min Range: -3.3585

Max Act: 2.8044. Min Act: -0.0000

Data Index: 1197827 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 3.3585. Min Range: -3.3585

Max Act: 2.7779. Min Act: -0.0000

Data Index: 1003997 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 3.3585. Min Range: -3.3585

Max Act: 2.8157. Min Act: -0.0000

Data Index: 299645 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 3.3585. Min Range: -3.3585

Max Act: 2.5861. Min Act: -0.0000

Data Index: 1351578 (C4 (Web Text))

Max Activating Token Index: 157

Text #10

Max Range: 3.3585. Min Range: -3.3585

Max Act: 2.5923. Min Act: -0.0000

Data Index: 699545 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 3.3585. Min Range: -3.3585

Max Act: 2.5630. Min Act: -0.0000

Data Index: 1124054 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 3.3585. Min Range: -3.3585

Max Act: 2.3706. Min Act: -0.0000

Data Index: 1138669 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 3.3585. Min Range: -3.3585

Max Act: 2.4879. Min Act: -0.0000

Data Index: 795290 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 3.3585. Min Range: -3.3585

Max Act: 2.5436. Min Act: -0.0000

Data Index: 463463 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 3.3585. Min Range: -3.3585

Max Act: 2.3449. Min Act: -0.0000

Data Index: 963193 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 3.3585. Min Range: -3.3585

Max Act: 2.2828. Min Act: -0.0000

Data Index: 1226584 (C4 (Web Text))

Max Activating Token Index: 784

Text #17

Max Range: 3.3585. Min Range: -3.3585

Max Act: 2.6372. Min Act: -0.0000

Data Index: 1339919 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 3.3585. Min Range: -3.3585

Max Act: 2.4549. Min Act: -0.0000

Data Index: 1107956 (C4 (Web Text))

Max Activating Token Index: 450

Text #19

Max Range: 3.3585. Min Range: -3.3585

Max Act: 2.4432. Min Act: -0.0000

Data Index: 11128 (C4 (Web Text))

Max Activating Token Index: 952