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

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

Neuron 2552 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6439. Min Range: -4.6439

Max Act: 4.6439. Min Act: -0.0000

Data Index: 349538 (C4 (Web Text))

Max Activating Token Index: 340

Text #1

Max Range: 4.6439. Min Range: -4.6439

Max Act: 4.3872. Min Act: -0.0000

Data Index: 43914 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 4.6439. Min Range: -4.6439

Max Act: 4.2620. Min Act: -0.0000

Data Index: 1001985 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 4.6439. Min Range: -4.6439

Max Act: 2.4179. Min Act: -0.0000

Data Index: 584036 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 4.6439. Min Range: -4.6439

Max Act: 2.5044. Min Act: -0.0000

Data Index: 818892 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 4.6439. Min Range: -4.6439

Max Act: 2.4398. Min Act: -0.0000

Data Index: 1225884 (C4 (Web Text))

Max Activating Token Index: 678

Text #6

Max Range: 4.6439. Min Range: -4.6439

Max Act: 2.4358. Min Act: -0.0000

Data Index: 497612 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 4.6439. Min Range: -4.6439

Max Act: 2.3722. Min Act: -0.0000

Data Index: 793427 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 4.6439. Min Range: -4.6439

Max Act: 2.2886. Min Act: -0.0000

Data Index: 279898 (C4 (Web Text))

Max Activating Token Index: 954

Text #9

Max Range: 4.6439. Min Range: -4.6439

Max Act: 2.1641. Min Act: -0.0000

Data Index: 40954 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 4.6439. Min Range: -4.6439

Max Act: 2.3771. Min Act: -0.0000

Data Index: 1338236 (C4 (Web Text))

Max Activating Token Index: 1013

Text #11

Max Range: 4.6439. Min Range: -4.6439

Max Act: 2.3788. Min Act: -0.0000

Data Index: 1297362 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 4.6439. Min Range: -4.6439

Max Act: 2.1157. Min Act: -0.0000

Data Index: 366674 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 4.6439. Min Range: -4.6439

Max Act: 2.2395. Min Act: -0.0000

Data Index: 1204897 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 4.6439. Min Range: -4.6439

Max Act: 2.2853. Min Act: -0.0000

Data Index: 1261453 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 4.6439. Min Range: -4.6439

Max Act: 2.1483. Min Act: -0.0000

Data Index: 652322 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 4.6439. Min Range: -4.6439

Max Act: 1.9999. Min Act: -0.0000

Data Index: 265564 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 4.6439. Min Range: -4.6439

Max Act: 2.1026. Min Act: -0.0000

Data Index: 793215 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 4.6439. Min Range: -4.6439

Max Act: 2.0860. Min Act: -0.0000

Data Index: 1346706 (C4 (Web Text))

Max Activating Token Index: 954

Text #19

Max Range: 4.6439. Min Range: -4.6439

Max Act: 1.9778. Min Act: -0.0000

Data Index: 73515 (C4 (Web Text))

Max Activating Token Index: 895