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

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

Neuron 76 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5216. Min Range: -2.5216

Max Act: 2.5216. Min Act: 0.0000

Data Index: 920847 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 2.5216. Min Range: -2.5216

Max Act: 2.1819. Min Act: 0.0000

Data Index: 102388 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 2.5216. Min Range: -2.5216

Max Act: 1.8475. Min Act: -0.0000

Data Index: 1324614 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 2.5216. Min Range: -2.5216

Max Act: 1.7915. Min Act: 0.0002

Data Index: 573320 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 2.5216. Min Range: -2.5216

Max Act: 1.6317. Min Act: 0.0000

Data Index: 195106 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 2.5216. Min Range: -2.5216

Max Act: 1.6889. Min Act: 0.0000

Data Index: 67048 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 2.5216. Min Range: -2.5216

Max Act: 1.6214. Min Act: -0.0000

Data Index: 1296065 (C4 (Web Text))

Max Activating Token Index: 571

Text #7

Max Range: 2.5216. Min Range: -2.5216

Max Act: 1.4660. Min Act: -0.0000

Data Index: 99322 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 2.5216. Min Range: -2.5216

Max Act: 1.5088. Min Act: -0.0000

Data Index: 531748 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 2.5216. Min Range: -2.5216

Max Act: 1.4995. Min Act: -0.0000

Data Index: 188033 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 2.5216. Min Range: -2.5216

Max Act: 1.4342. Min Act: -0.0000

Data Index: 855753 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 2.5216. Min Range: -2.5216

Max Act: 1.4763. Min Act: -0.0000

Data Index: 266286 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 2.5216. Min Range: -2.5216

Max Act: 1.3366. Min Act: 0.0000

Data Index: 1211824 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 2.5216. Min Range: -2.5216

Max Act: 1.3186. Min Act: -0.0000

Data Index: 545610 (C4 (Web Text))

Max Activating Token Index: 352

Text #14

Max Range: 2.5216. Min Range: -2.5216

Max Act: 1.3219. Min Act: -0.0000

Data Index: 321308 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 2.5216. Min Range: -2.5216

Max Act: 1.3762. Min Act: -0.0000

Data Index: 305023 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 2.5216. Min Range: -2.5216

Max Act: 1.3477. Min Act: -0.0000

Data Index: 947808 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 2.5216. Min Range: -2.5216

Max Act: 1.3051. Min Act: -0.0000

Data Index: 721771 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 2.5216. Min Range: -2.5216

Max Act: 1.2394. Min Act: -0.0000

Data Index: 987591 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 2.5216. Min Range: -2.5216

Max Act: 1.2476. Min Act: 0.0000

Data Index: 712294 (C4 (Web Text))

Max Activating Token Index: 683