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

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

Neuron 4879 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4101. Min Range: -1.4101

Max Act: 1.4101. Min Act: -0.0000

Data Index: 916588 (C4 (Web Text))

Max Activating Token Index: 224

Text #1

Max Range: 1.4101. Min Range: -1.4101

Max Act: 1.3987. Min Act: -0.0000

Data Index: 345420 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 1.4101. Min Range: -1.4101

Max Act: 1.1040. Min Act: -0.0000

Data Index: 1221742 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 1.4101. Min Range: -1.4101

Max Act: 1.0683. Min Act: -0.0000

Data Index: 89531 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 1.4101. Min Range: -1.4101

Max Act: 1.1102. Min Act: -0.0000

Data Index: 1126943 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 1.4101. Min Range: -1.4101

Max Act: 1.0932. Min Act: -0.0000

Data Index: 1076402 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 1.4101. Min Range: -1.4101

Max Act: 1.0788. Min Act: -0.0000

Data Index: 1212851 (C4 (Web Text))

Max Activating Token Index: 441

Text #7

Max Range: 1.4101. Min Range: -1.4101

Max Act: 1.0179. Min Act: -0.0000

Data Index: 271223 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 1.4101. Min Range: -1.4101

Max Act: 0.9087. Min Act: -0.0000

Data Index: 803154 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 1.4101. Min Range: -1.4101

Max Act: 0.9677. Min Act: -0.0000

Data Index: 1264820 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 1.4101. Min Range: -1.4101

Max Act: 1.0264. Min Act: -0.0000

Data Index: 654298 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 1.4101. Min Range: -1.4101

Max Act: 1.0498. Min Act: -0.0000

Data Index: 73854 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 1.4101. Min Range: -1.4101

Max Act: 1.0459. Min Act: -0.0000

Data Index: 738867 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 1.4101. Min Range: -1.4101

Max Act: 1.0391. Min Act: -0.0000

Data Index: 1413598 (Python Code)

Max Activating Token Index: 883

Text #14

Max Range: 1.4101. Min Range: -1.4101

Max Act: 0.9533. Min Act: -0.0000

Data Index: 1124256 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 1.4101. Min Range: -1.4101

Max Act: 1.0624. Min Act: -0.0000

Data Index: 966409 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 1.4101. Min Range: -1.4101

Max Act: 0.9641. Min Act: -0.0000

Data Index: 850270 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 1.4101. Min Range: -1.4101

Max Act: 0.9309. Min Act: -0.0000

Data Index: 694144 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 1.4101. Min Range: -1.4101

Max Act: 0.9510. Min Act: -0.0000

Data Index: 839938 (C4 (Web Text))

Max Activating Token Index: 381

Text #19

Max Range: 1.4101. Min Range: -1.4101

Max Act: 1.0151. Min Act: -0.0000

Data Index: 1266958 (C4 (Web Text))

Max Activating Token Index: 509