Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2814 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.7455. Min Range: -2.7455

Max Act: 2.7455. Min Act: -0.0001

Data Index: 684658 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 2.7455. Min Range: -2.7455

Max Act: 2.7335. Min Act: -0.0001

Data Index: 940180 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 2.7455. Min Range: -2.7455

Max Act: 2.2835. Min Act: -0.0000

Data Index: 1345355 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 2.7455. Min Range: -2.7455

Max Act: 2.1678. Min Act: -0.0001

Data Index: 751160 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 2.7455. Min Range: -2.7455

Max Act: 2.0138. Min Act: -0.0000

Data Index: 1157085 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 2.7455. Min Range: -2.7455

Max Act: 2.0164. Min Act: -0.0000

Data Index: 805963 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 2.7455. Min Range: -2.7455

Max Act: 2.0966. Min Act: -0.0001

Data Index: 77494 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 2.7455. Min Range: -2.7455

Max Act: 2.3527. Min Act: -0.0000

Data Index: 380230 (C4 (Web Text))

Max Activating Token Index: 902

Text #8

Max Range: 2.7455. Min Range: -2.7455

Max Act: 1.7892. Min Act: -0.0001

Data Index: 954761 (C4 (Web Text))

Max Activating Token Index: 893

Text #9

Max Range: 2.7455. Min Range: -2.7455

Max Act: 1.7227. Min Act: -0.0001

Data Index: 1332200 (C4 (Web Text))

Max Activating Token Index: 815

Text #10

Max Range: 2.7455. Min Range: -2.7455

Max Act: 1.9298. Min Act: -0.0001

Data Index: 325931 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 2.7455. Min Range: -2.7455

Max Act: 1.6994. Min Act: -0.0000

Data Index: 1064482 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 2.7455. Min Range: -2.7455

Max Act: 1.7699. Min Act: -0.0000

Data Index: 549143 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 2.7455. Min Range: -2.7455

Max Act: 1.5295. Min Act: -0.0000

Data Index: 941263 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 2.7455. Min Range: -2.7455

Max Act: 1.5514. Min Act: -0.0001

Data Index: 881295 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 2.7455. Min Range: -2.7455

Max Act: 1.5768. Min Act: -0.0000

Data Index: 994892 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 2.7455. Min Range: -2.7455

Max Act: 1.7643. Min Act: -0.0000

Data Index: 1258025 (C4 (Web Text))

Max Activating Token Index: 674

Text #17

Max Range: 2.7455. Min Range: -2.7455

Max Act: 1.5715. Min Act: -0.0000

Data Index: 993268 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 2.7455. Min Range: -2.7455

Max Act: 1.6120. Min Act: -0.0000

Data Index: 1201417 (C4 (Web Text))

Max Activating Token Index: 282

Text #19

Max Range: 2.7455. Min Range: -2.7455

Max Act: 1.6156. Min Act: -0.0000

Data Index: 751525 (C4 (Web Text))

Max Activating Token Index: 482