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

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

Neuron 3217 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7011. Min Range: -2.7011

Max Act: 2.7011. Min Act: -0.0000

Data Index: 99268 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 2.7011. Min Range: -2.7011

Max Act: 2.6759. Min Act: -0.0000

Data Index: 350014 (C4 (Web Text))

Max Activating Token Index: 675

Text #2

Max Range: 2.7011. Min Range: -2.7011

Max Act: 2.4119. Min Act: -0.0000

Data Index: 1164715 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 2.7011. Min Range: -2.7011

Max Act: 2.3824. Min Act: -0.0000

Data Index: 1224431 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 2.7011. Min Range: -2.7011

Max Act: 2.4475. Min Act: -0.0000

Data Index: 953140 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 2.7011. Min Range: -2.7011

Max Act: 2.5318. Min Act: -0.0000

Data Index: 210840 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 2.7011. Min Range: -2.7011

Max Act: 2.2333. Min Act: -0.0000

Data Index: 852742 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 2.7011. Min Range: -2.7011

Max Act: 2.3432. Min Act: -0.0000

Data Index: 1101954 (C4 (Web Text))

Max Activating Token Index: 882

Text #8

Max Range: 2.7011. Min Range: -2.7011

Max Act: 2.3327. Min Act: -0.0000

Data Index: 1085058 (C4 (Web Text))

Max Activating Token Index: 283

Text #9

Max Range: 2.7011. Min Range: -2.7011

Max Act: 2.2074. Min Act: -0.0000

Data Index: 315238 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 2.7011. Min Range: -2.7011

Max Act: 2.3000. Min Act: -0.0000

Data Index: 828925 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 2.7011. Min Range: -2.7011

Max Act: 2.3064. Min Act: -0.0000

Data Index: 809489 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 2.7011. Min Range: -2.7011

Max Act: 2.1594. Min Act: -0.0000

Data Index: 389753 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 2.7011. Min Range: -2.7011

Max Act: 2.2579. Min Act: -0.0000

Data Index: 606841 (C4 (Web Text))

Max Activating Token Index: 803

Text #14

Max Range: 2.7011. Min Range: -2.7011

Max Act: 2.3882. Min Act: -0.0000

Data Index: 742233 (C4 (Web Text))

Max Activating Token Index: 698

Text #15

Max Range: 2.7011. Min Range: -2.7011

Max Act: 2.2341. Min Act: -0.0000

Data Index: 1284243 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 2.7011. Min Range: -2.7011

Max Act: 2.2191. Min Act: -0.0000

Data Index: 1107481 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 2.7011. Min Range: -2.7011

Max Act: 2.3547. Min Act: -0.0000

Data Index: 328877 (C4 (Web Text))

Max Activating Token Index: 260

Text #18

Max Range: 2.7011. Min Range: -2.7011

Max Act: 2.1031. Min Act: -0.0000

Data Index: 478564 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 2.7011. Min Range: -2.7011

Max Act: 2.2197. Min Act: -0.0000

Data Index: 1280362 (C4 (Web Text))

Max Activating Token Index: 452