Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2616 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2385. Min Act: -0.0001

Data Index: 696941 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2289. Min Act: -0.0001

Data Index: 1354795 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2197. Min Act: -0.0001

Data Index: 790622 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2279. Min Act: -0.0001

Data Index: 1141834 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2065. Min Act: -0.0000

Data Index: 286371 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2067. Min Act: -0.0000

Data Index: 44428 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2114. Min Act: -0.0001

Data Index: 1291059 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2097. Min Act: -0.0001

Data Index: 608363 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2152. Min Act: -0.0001

Data Index: 1158702 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.1932. Min Act: -0.0001

Data Index: 1187065 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.1955. Min Act: -0.0001

Data Index: 647995 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.1946. Min Act: -0.0001

Data Index: 1174807 (C4 (Web Text))

Max Activating Token Index: 629

Text #12

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.1907. Min Act: -0.0001

Data Index: 1294984 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.1905. Min Act: -0.0001

Data Index: 1253317 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.1900. Min Act: -0.0001

Data Index: 974108 (C4 (Web Text))

Max Activating Token Index: 719

Text #15

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.1852. Min Act: -0.0001

Data Index: 187258 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.1874. Min Act: -0.0001

Data Index: 519724 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.1890. Min Act: -0.0001

Data Index: 515631 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.1808. Min Act: -0.0001

Data Index: 959686 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.1788. Min Act: -0.0001

Data Index: 250047 (C4 (Web Text))

Max Activating Token Index: 786