Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 77 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4527. Min Range: -2.4527

Max Act: 2.4527. Min Act: -0.0000

Data Index: 115702 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 2.4527. Min Range: -2.4527

Max Act: 2.2766. Min Act: -0.0000

Data Index: 879730 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 2.4527. Min Range: -2.4527

Max Act: 1.9956. Min Act: -0.0000

Data Index: 1223584 (C4 (Web Text))

Max Activating Token Index: 953

Text #3

Max Range: 2.4527. Min Range: -2.4527

Max Act: 1.9070. Min Act: -0.0000

Data Index: 311077 (C4 (Web Text))

Max Activating Token Index: 930

Text #4

Max Range: 2.4527. Min Range: -2.4527

Max Act: 1.1892. Min Act: -0.0000

Data Index: 131941 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 2.4527. Min Range: -2.4527

Max Act: 1.1284. Min Act: -0.0000

Data Index: 705103 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 2.4527. Min Range: -2.4527

Max Act: 1.0259. Min Act: -0.0000

Data Index: 1197688 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 2.4527. Min Range: -2.4527

Max Act: 0.9112. Min Act: -0.0000

Data Index: 1145154 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 2.4527. Min Range: -2.4527

Max Act: 0.9585. Min Act: -0.0000

Data Index: 587109 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 2.4527. Min Range: -2.4527

Max Act: 0.9139. Min Act: -0.0000

Data Index: 171554 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 2.4527. Min Range: -2.4527

Max Act: 1.0078. Min Act: -0.0000

Data Index: 1056333 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 2.4527. Min Range: -2.4527

Max Act: 0.9672. Min Act: -0.0000

Data Index: 503399 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 2.4527. Min Range: -2.4527

Max Act: 0.9036. Min Act: -0.0000

Data Index: 441453 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 2.4527. Min Range: -2.4527

Max Act: 0.9234. Min Act: -0.0000

Data Index: 578195 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 2.4527. Min Range: -2.4527

Max Act: 0.8005. Min Act: -0.0000

Data Index: 862948 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 2.4527. Min Range: -2.4527

Max Act: 0.9561. Min Act: -0.0000

Data Index: 25695 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 2.4527. Min Range: -2.4527

Max Act: 0.9770. Min Act: -0.0000

Data Index: 760424 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 2.4527. Min Range: -2.4527

Max Act: 0.9775. Min Act: -0.0000

Data Index: 363204 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 2.4527. Min Range: -2.4527

Max Act: 1.0008. Min Act: -0.0000

Data Index: 84902 (C4 (Web Text))

Max Activating Token Index: 418

Text #19

Max Range: 2.4527. Min Range: -2.4527

Max Act: 0.8625. Min Act: -0.0000

Data Index: 96434 (C4 (Web Text))

Max Activating Token Index: 122