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

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

Neuron 5201 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: 1.2954. Min Range: -1.2954

Max Act: 1.2954. Min Act: -0.0002

Data Index: 249811 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 1.2954. Min Range: -1.2954

Max Act: 1.2194. Min Act: -0.0002

Data Index: 1479956 (Python Code)

Max Activating Token Index: 348

Text #2

Max Range: 1.2954. Min Range: -1.2954

Max Act: 1.1871. Min Act: -0.0002

Data Index: 713687 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 1.2954. Min Range: -1.2954

Max Act: 1.1547. Min Act: -0.0002

Data Index: 263898 (C4 (Web Text))

Max Activating Token Index: 321

Text #4

Max Range: 1.2954. Min Range: -1.2954

Max Act: 1.1435. Min Act: -0.0002

Data Index: 1024440 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 1.2954. Min Range: -1.2954

Max Act: 1.0269. Min Act: -0.0002

Data Index: 152496 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 1.2954. Min Range: -1.2954

Max Act: 1.0047. Min Act: -0.0002

Data Index: 930775 (C4 (Web Text))

Max Activating Token Index: 558

Text #7

Max Range: 1.2954. Min Range: -1.2954

Max Act: 1.0203. Min Act: -0.0002

Data Index: 1331407 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 1.2954. Min Range: -1.2954

Max Act: 1.0230. Min Act: -0.0002

Data Index: 152394 (C4 (Web Text))

Max Activating Token Index: 962

Text #9

Max Range: 1.2954. Min Range: -1.2954

Max Act: 1.0244. Min Act: -0.0002

Data Index: 14310 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 1.2954. Min Range: -1.2954

Max Act: 0.9959. Min Act: -0.0002

Data Index: 448293 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 1.2954. Min Range: -1.2954

Max Act: 1.0024. Min Act: -0.0002

Data Index: 251590 (C4 (Web Text))

Max Activating Token Index: 702

Text #12

Max Range: 1.2954. Min Range: -1.2954

Max Act: 1.0184. Min Act: -0.0002

Data Index: 323619 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 1.2954. Min Range: -1.2954

Max Act: 1.0221. Min Act: -0.0002

Data Index: 936105 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 1.2954. Min Range: -1.2954

Max Act: 1.0002. Min Act: -0.0002

Data Index: 506103 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 1.2954. Min Range: -1.2954

Max Act: 0.9872. Min Act: -0.0002

Data Index: 493963 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 1.2954. Min Range: -1.2954

Max Act: 0.9890. Min Act: -0.0002

Data Index: 416989 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 1.2954. Min Range: -1.2954

Max Act: 1.0041. Min Act: -0.0002

Data Index: 192816 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 1.2954. Min Range: -1.2954

Max Act: 0.9696. Min Act: -0.0002

Data Index: 672518 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 1.2954. Min Range: -1.2954

Max Act: 0.9429. Min Act: -0.0002

Data Index: 480056 (C4 (Web Text))

Max Activating Token Index: 817