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

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

Neuron 803 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8268. Min Range: -4.8268

Max Act: 4.6815. Min Act: -0.0000

Data Index: 719456 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 4.8268. Min Range: -4.8268

Max Act: 4.8268. Min Act: -0.0000

Data Index: 580976 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 4.8268. Min Range: -4.8268

Max Act: 4.3491. Min Act: -0.0000

Data Index: 119026 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 4.8268. Min Range: -4.8268

Max Act: 3.8509. Min Act: -0.0000

Data Index: 1539308 (Python Code)

Max Activating Token Index: 288

Text #4

Max Range: 4.8268. Min Range: -4.8268

Max Act: 3.9981. Min Act: -0.0000

Data Index: 871325 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 4.8268. Min Range: -4.8268

Max Act: 3.9183. Min Act: -0.0000

Data Index: 500528 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 4.8268. Min Range: -4.8268

Max Act: 4.2365. Min Act: -0.0000

Data Index: 620025 (C4 (Web Text))

Max Activating Token Index: 495

Text #7

Max Range: 4.8268. Min Range: -4.8268

Max Act: 3.8758. Min Act: -0.0000

Data Index: 513839 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 4.8268. Min Range: -4.8268

Max Act: 4.0005. Min Act: -0.0000

Data Index: 1180 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 4.8268. Min Range: -4.8268

Max Act: 3.7937. Min Act: -0.0000

Data Index: 733067 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 4.8268. Min Range: -4.8268

Max Act: 3.9185. Min Act: -0.0000

Data Index: 525557 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 4.8268. Min Range: -4.8268

Max Act: 3.7432. Min Act: -0.0000

Data Index: 111707 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 4.8268. Min Range: -4.8268

Max Act: 3.8990. Min Act: -0.0000

Data Index: 442307 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 4.8268. Min Range: -4.8268

Max Act: 4.0387. Min Act: -0.0000

Data Index: 726051 (C4 (Web Text))

Max Activating Token Index: 307

Text #14

Max Range: 4.8268. Min Range: -4.8268

Max Act: 3.8628. Min Act: -0.0000

Data Index: 1013987 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 4.8268. Min Range: -4.8268

Max Act: 3.9725. Min Act: -0.0000

Data Index: 804163 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 4.8268. Min Range: -4.8268

Max Act: 3.4637. Min Act: -0.0000

Data Index: 530941 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 4.8268. Min Range: -4.8268

Max Act: 3.7886. Min Act: -0.0000

Data Index: 1029909 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 4.8268. Min Range: -4.8268

Max Act: 3.7857. Min Act: -0.0000

Data Index: 239942 (C4 (Web Text))

Max Activating Token Index: 995

Text #19

Max Range: 4.8268. Min Range: -4.8268

Max Act: 3.7472. Min Act: -0.0000

Data Index: 183297 (C4 (Web Text))

Max Activating Token Index: 470