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

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

Neuron 326 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2940. Min Range: -3.2940

Max Act: 3.2940. Min Act: -0.0001

Data Index: 668683 (C4 (Web Text))

Max Activating Token Index: 246

Text #1

Max Range: 3.2940. Min Range: -3.2940

Max Act: 2.7498. Min Act: -0.0001

Data Index: 16288 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 3.2940. Min Range: -3.2940

Max Act: 2.6964. Min Act: -0.0001

Data Index: 148872 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 3.2940. Min Range: -3.2940

Max Act: 2.1871. Min Act: -0.0001

Data Index: 454767 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 3.2940. Min Range: -3.2940

Max Act: 2.2163. Min Act: -0.0001

Data Index: 513162 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 3.2940. Min Range: -3.2940

Max Act: 2.1435. Min Act: -0.0001

Data Index: 1201683 (C4 (Web Text))

Max Activating Token Index: 533

Text #6

Max Range: 3.2940. Min Range: -3.2940

Max Act: 2.0510. Min Act: -0.0001

Data Index: 1034780 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 3.2940. Min Range: -3.2940

Max Act: 2.0325. Min Act: -0.0001

Data Index: 1250773 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 3.2940. Min Range: -3.2940

Max Act: 1.8973. Min Act: -0.0001

Data Index: 137178 (C4 (Web Text))

Max Activating Token Index: 158

Text #9

Max Range: 3.2940. Min Range: -3.2940

Max Act: 2.0910. Min Act: -0.0001

Data Index: 1073895 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 3.2940. Min Range: -3.2940

Max Act: 1.9429. Min Act: -0.0001

Data Index: 964515 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 3.2940. Min Range: -3.2940

Max Act: 1.9391. Min Act: -0.0001

Data Index: 723706 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 3.2940. Min Range: -3.2940

Max Act: 2.0314. Min Act: -0.0001

Data Index: 1287196 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 3.2940. Min Range: -3.2940

Max Act: 1.8233. Min Act: -0.0001

Data Index: 16252 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 3.2940. Min Range: -3.2940

Max Act: 2.0315. Min Act: -0.0001

Data Index: 335628 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 3.2940. Min Range: -3.2940

Max Act: 1.8824. Min Act: -0.0001

Data Index: 811959 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 3.2940. Min Range: -3.2940

Max Act: 1.8944. Min Act: -0.0001

Data Index: 176678 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 3.2940. Min Range: -3.2940

Max Act: 1.8644. Min Act: -0.0001

Data Index: 137232 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 3.2940. Min Range: -3.2940

Max Act: 1.7822. Min Act: -0.0001

Data Index: 595726 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 3.2940. Min Range: -3.2940

Max Act: 1.8599. Min Act: -0.0001

Data Index: 500260 (C4 (Web Text))

Max Activating Token Index: 12