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

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

Neuron 717 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.5286. Min Range: -6.5286

Max Act: 6.5114. Min Act: -0.0000

Data Index: 1235127 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 6.5286. Min Range: -6.5286

Max Act: 6.5286. Min Act: -0.0000

Data Index: 810644 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 6.5286. Min Range: -6.5286

Max Act: 6.4691. Min Act: -0.0000

Data Index: 443423 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 6.5286. Min Range: -6.5286

Max Act: 6.0720. Min Act: -0.0000

Data Index: 1005689 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 6.5286. Min Range: -6.5286

Max Act: 5.5070. Min Act: -0.0000

Data Index: 712170 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 6.5286. Min Range: -6.5286

Max Act: 6.3381. Min Act: -0.0000

Data Index: 297954 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 6.5286. Min Range: -6.5286

Max Act: 5.9146. Min Act: 0.0000

Data Index: 34428 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 6.5286. Min Range: -6.5286

Max Act: 5.5780. Min Act: -0.0000

Data Index: 318962 (C4 (Web Text))

Max Activating Token Index: 490

Text #8

Max Range: 6.5286. Min Range: -6.5286

Max Act: 5.8456. Min Act: -0.0000

Data Index: 316559 (C4 (Web Text))

Max Activating Token Index: 481

Text #9

Max Range: 6.5286. Min Range: -6.5286

Max Act: 5.6435. Min Act: -0.0000

Data Index: 261076 (C4 (Web Text))

Max Activating Token Index: 673

Text #10

Max Range: 6.5286. Min Range: -6.5286

Max Act: 5.3782. Min Act: -0.0000

Data Index: 509317 (C4 (Web Text))

Max Activating Token Index: 135

Text #11

Max Range: 6.5286. Min Range: -6.5286

Max Act: 5.4265. Min Act: -0.0000

Data Index: 293484 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 6.5286. Min Range: -6.5286

Max Act: 5.4198. Min Act: -0.0000

Data Index: 1081935 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 6.5286. Min Range: -6.5286

Max Act: 5.3918. Min Act: -0.0000

Data Index: 1238209 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 6.5286. Min Range: -6.5286

Max Act: 5.3247. Min Act: -0.0000

Data Index: 1131758 (C4 (Web Text))

Max Activating Token Index: 440

Text #15

Max Range: 6.5286. Min Range: -6.5286

Max Act: 5.1555. Min Act: -0.0000

Data Index: 906947 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 6.5286. Min Range: -6.5286

Max Act: 5.4819. Min Act: -0.0000

Data Index: 1237443 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 6.5286. Min Range: -6.5286

Max Act: 5.4484. Min Act: -0.0000

Data Index: 1358645 (C4 (Web Text))

Max Activating Token Index: 289

Text #18

Max Range: 6.5286. Min Range: -6.5286

Max Act: 5.0457. Min Act: -0.0000

Data Index: 1359192 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 6.5286. Min Range: -6.5286

Max Act: 5.1331. Min Act: -0.0000

Data Index: 657142 (C4 (Web Text))

Max Activating Token Index: 796