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

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

Neuron 1396 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2330. Min Range: -3.2330

Max Act: 3.2303. Min Act: -0.0000

Data Index: 1271118 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 3.2330. Min Range: -3.2330

Max Act: 3.2330. Min Act: -0.0000

Data Index: 1353267 (C4 (Web Text))

Max Activating Token Index: 652

Text #2

Max Range: 3.2330. Min Range: -3.2330

Max Act: 3.2069. Min Act: -0.0000

Data Index: 1290633 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 3.2330. Min Range: -3.2330

Max Act: 2.9805. Min Act: -0.0000

Data Index: 675216 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 3.2330. Min Range: -3.2330

Max Act: 2.9555. Min Act: -0.0000

Data Index: 722345 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 3.2330. Min Range: -3.2330

Max Act: 2.8103. Min Act: -0.0000

Data Index: 639617 (C4 (Web Text))

Max Activating Token Index: 933

Text #6

Max Range: 3.2330. Min Range: -3.2330

Max Act: 2.9192. Min Act: -0.0000

Data Index: 631616 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 3.2330. Min Range: -3.2330

Max Act: 2.9239. Min Act: -0.0000

Data Index: 759140 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 3.2330. Min Range: -3.2330

Max Act: 2.7495. Min Act: -0.0000

Data Index: 32012 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 3.2330. Min Range: -3.2330

Max Act: 2.8378. Min Act: -0.0000

Data Index: 223053 (C4 (Web Text))

Max Activating Token Index: 446

Text #10

Max Range: 3.2330. Min Range: -3.2330

Max Act: 2.7567. Min Act: -0.0000

Data Index: 972046 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 3.2330. Min Range: -3.2330

Max Act: 2.7114. Min Act: -0.0000

Data Index: 604217 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 3.2330. Min Range: -3.2330

Max Act: 2.6900. Min Act: -0.0000

Data Index: 313895 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 3.2330. Min Range: -3.2330

Max Act: 2.6274. Min Act: -0.0000

Data Index: 787625 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 3.2330. Min Range: -3.2330

Max Act: 2.5575. Min Act: -0.0000

Data Index: 880090 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 3.2330. Min Range: -3.2330

Max Act: 2.5554. Min Act: -0.0000

Data Index: 600027 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 3.2330. Min Range: -3.2330

Max Act: 2.5494. Min Act: -0.0000

Data Index: 975766 (C4 (Web Text))

Max Activating Token Index: 894

Text #17

Max Range: 3.2330. Min Range: -3.2330

Max Act: 2.5120. Min Act: -0.0000

Data Index: 1266693 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 3.2330. Min Range: -3.2330

Max Act: 2.6174. Min Act: -0.0000

Data Index: 907132 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 3.2330. Min Range: -3.2330

Max Act: 2.4399. Min Act: -0.0000

Data Index: 86020 (C4 (Web Text))

Max Activating Token Index: 297