Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3758 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4384. Min Range: -1.4384

Max Act: 1.4384. Min Act: -0.0000

Data Index: 359543 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 1.4384. Min Range: -1.4384

Max Act: 1.1039. Min Act: -0.0000

Data Index: 437469 (C4 (Web Text))

Max Activating Token Index: 902

Text #2

Max Range: 1.4384. Min Range: -1.4384

Max Act: 1.0188. Min Act: -0.0000

Data Index: 354124 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 1.4384. Min Range: -1.4384

Max Act: 1.1252. Min Act: -0.0000

Data Index: 678844 (C4 (Web Text))

Max Activating Token Index: 959

Text #4

Max Range: 1.4384. Min Range: -1.4384

Max Act: 0.9913. Min Act: -0.0000

Data Index: 431419 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 1.4384. Min Range: -1.4384

Max Act: 1.0358. Min Act: -0.0000

Data Index: 922560 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 1.4384. Min Range: -1.4384

Max Act: 1.0050. Min Act: -0.0000

Data Index: 774132 (C4 (Web Text))

Max Activating Token Index: 485

Text #7

Max Range: 1.4384. Min Range: -1.4384

Max Act: 0.9568. Min Act: -0.0000

Data Index: 850717 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 1.4384. Min Range: -1.4384

Max Act: 0.9249. Min Act: -0.0000

Data Index: 1045187 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 1.4384. Min Range: -1.4384

Max Act: 0.9480. Min Act: -0.0000

Data Index: 257483 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 1.4384. Min Range: -1.4384

Max Act: 0.9009. Min Act: -0.0000

Data Index: 632376 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 1.4384. Min Range: -1.4384

Max Act: 0.8897. Min Act: -0.0000

Data Index: 768406 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 1.4384. Min Range: -1.4384

Max Act: 0.9468. Min Act: -0.0000

Data Index: 1071000 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 1.4384. Min Range: -1.4384

Max Act: 0.9394. Min Act: -0.0000

Data Index: 155654 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 1.4384. Min Range: -1.4384

Max Act: 0.9090. Min Act: -0.0000

Data Index: 302659 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 1.4384. Min Range: -1.4384

Max Act: 0.9103. Min Act: -0.0000

Data Index: 1013218 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 1.4384. Min Range: -1.4384

Max Act: 0.9963. Min Act: -0.0000

Data Index: 77879 (C4 (Web Text))

Max Activating Token Index: 212

Text #17

Max Range: 1.4384. Min Range: -1.4384

Max Act: 0.8717. Min Act: -0.0000

Data Index: 478014 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 1.4384. Min Range: -1.4384

Max Act: 0.9146. Min Act: -0.0000

Data Index: 694920 (C4 (Web Text))

Max Activating Token Index: 564

Text #19

Max Range: 1.4384. Min Range: -1.4384

Max Act: 0.8581. Min Act: -0.0000

Data Index: 403244 (C4 (Web Text))

Max Activating Token Index: 548