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

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

Neuron 2635 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4856. Min Range: -5.4856

Max Act: 5.4856. Min Act: -0.0001

Data Index: 164549 (C4 (Web Text))

Max Activating Token Index: 234

Text #1

Max Range: 5.4856. Min Range: -5.4856

Max Act: 4.3113. Min Act: -0.0001

Data Index: 169336 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 5.4856. Min Range: -5.4856

Max Act: 4.1630. Min Act: -0.0001

Data Index: 296280 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 5.4856. Min Range: -5.4856

Max Act: 3.8134. Min Act: -0.0001

Data Index: 1326883 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 5.4856. Min Range: -5.4856

Max Act: 3.6268. Min Act: -0.0001

Data Index: 983742 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 5.4856. Min Range: -5.4856

Max Act: 3.1555. Min Act: -0.0001

Data Index: 517979 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 5.4856. Min Range: -5.4856

Max Act: 3.3391. Min Act: -0.0001

Data Index: 1025100 (C4 (Web Text))

Max Activating Token Index: 68

Text #7

Max Range: 5.4856. Min Range: -5.4856

Max Act: 3.1653. Min Act: -0.0001

Data Index: 346271 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 5.4856. Min Range: -5.4856

Max Act: 3.1278. Min Act: -0.0001

Data Index: 1295813 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 5.4856. Min Range: -5.4856

Max Act: 3.2561. Min Act: -0.0001

Data Index: 993188 (C4 (Web Text))

Max Activating Token Index: 404

Text #10

Max Range: 5.4856. Min Range: -5.4856

Max Act: 3.4015. Min Act: -0.0001

Data Index: 1063704 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 5.4856. Min Range: -5.4856

Max Act: 3.2148. Min Act: -0.0001

Data Index: 111798 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 5.4856. Min Range: -5.4856

Max Act: 3.2150. Min Act: -0.0001

Data Index: 1068937 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 5.4856. Min Range: -5.4856

Max Act: 3.1972. Min Act: -0.0001

Data Index: 1120461 (C4 (Web Text))

Max Activating Token Index: 448

Text #14

Max Range: 5.4856. Min Range: -5.4856

Max Act: 3.3448. Min Act: -0.0001

Data Index: 1019027 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 5.4856. Min Range: -5.4856

Max Act: 2.9217. Min Act: -0.0001

Data Index: 666417 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 5.4856. Min Range: -5.4856

Max Act: 3.1732. Min Act: -0.0001

Data Index: 1207153 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 5.4856. Min Range: -5.4856

Max Act: 3.1527. Min Act: -0.0001

Data Index: 1258276 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 5.4856. Min Range: -5.4856

Max Act: 3.0126. Min Act: -0.0001

Data Index: 261916 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 5.4856. Min Range: -5.4856

Max Act: 2.9789. Min Act: -0.0001

Data Index: 9671 (C4 (Web Text))

Max Activating Token Index: 601