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

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

Neuron 1671 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2744. Min Range: -1.2744

Max Act: 1.2744. Min Act: -0.0001

Data Index: 954071 (C4 (Web Text))

Max Activating Token Index: 909

Text #1

Max Range: 1.2744. Min Range: -1.2744

Max Act: 0.9176. Min Act: -0.0001

Data Index: 47324 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 1.2744. Min Range: -1.2744

Max Act: 0.9230. Min Act: -0.0001

Data Index: 242122 (C4 (Web Text))

Max Activating Token Index: 448

Text #3

Max Range: 1.2744. Min Range: -1.2744

Max Act: 0.8305. Min Act: -0.0001

Data Index: 1275591 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 1.2744. Min Range: -1.2744

Max Act: 0.9042. Min Act: -0.0001

Data Index: 439076 (C4 (Web Text))

Max Activating Token Index: 671

Text #5

Max Range: 1.2744. Min Range: -1.2744

Max Act: 0.8268. Min Act: -0.0001

Data Index: 973707 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 1.2744. Min Range: -1.2744

Max Act: 0.8165. Min Act: -0.0001

Data Index: 594782 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 1.2744. Min Range: -1.2744

Max Act: 0.8515. Min Act: -0.0001

Data Index: 176916 (C4 (Web Text))

Max Activating Token Index: 434

Text #8

Max Range: 1.2744. Min Range: -1.2744

Max Act: 0.8476. Min Act: -0.0001

Data Index: 618827 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 1.2744. Min Range: -1.2744

Max Act: 0.8226. Min Act: -0.0001

Data Index: 48157 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 1.2744. Min Range: -1.2744

Max Act: 0.7990. Min Act: -0.0001

Data Index: 648879 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 1.2744. Min Range: -1.2744

Max Act: 0.8135. Min Act: -0.0001

Data Index: 416530 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 1.2744. Min Range: -1.2744

Max Act: 0.8576. Min Act: -0.0001

Data Index: 334315 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 1.2744. Min Range: -1.2744

Max Act: 0.7195. Min Act: -0.0001

Data Index: 1262346 (C4 (Web Text))

Max Activating Token Index: 503

Text #14

Max Range: 1.2744. Min Range: -1.2744

Max Act: 0.7426. Min Act: -0.0001

Data Index: 405591 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 1.2744. Min Range: -1.2744

Max Act: 0.7463. Min Act: -0.0001

Data Index: 230096 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 1.2744. Min Range: -1.2744

Max Act: 0.7459. Min Act: -0.0001

Data Index: 448511 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 1.2744. Min Range: -1.2744

Max Act: 0.7303. Min Act: -0.0001

Data Index: 884833 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 1.2744. Min Range: -1.2744

Max Act: 0.7789. Min Act: -0.0001

Data Index: 607077 (C4 (Web Text))

Max Activating Token Index: 245

Text #19

Max Range: 1.2744. Min Range: -1.2744

Max Act: 0.7236. Min Act: -0.0001

Data Index: 798427 (C4 (Web Text))

Max Activating Token Index: 632