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

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

Neuron 4853 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: 4.1908. Min Range: -4.1908

Max Act: 4.1908. Min Act: -0.0000

Data Index: 374604 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 4.1908. Min Range: -4.1908

Max Act: 4.0422. Min Act: -0.0000

Data Index: 176501 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 4.1908. Min Range: -4.1908

Max Act: 3.8324. Min Act: -0.0000

Data Index: 970814 (C4 (Web Text))

Max Activating Token Index: 499

Text #3

Max Range: 4.1908. Min Range: -4.1908

Max Act: 3.5337. Min Act: -0.0000

Data Index: 917192 (C4 (Web Text))

Max Activating Token Index: 950

Text #4

Max Range: 4.1908. Min Range: -4.1908

Max Act: 3.2645. Min Act: -0.0000

Data Index: 884484 (C4 (Web Text))

Max Activating Token Index: 771

Text #5

Max Range: 4.1908. Min Range: -4.1908

Max Act: 3.1702. Min Act: -0.0000

Data Index: 697614 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 4.1908. Min Range: -4.1908

Max Act: 2.9981. Min Act: -0.0000

Data Index: 963051 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 4.1908. Min Range: -4.1908

Max Act: 3.2511. Min Act: -0.0000

Data Index: 748488 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 4.1908. Min Range: -4.1908

Max Act: 3.1157. Min Act: -0.0000

Data Index: 792221 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 4.1908. Min Range: -4.1908

Max Act: 3.1031. Min Act: -0.0000

Data Index: 621662 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 4.1908. Min Range: -4.1908

Max Act: 2.8716. Min Act: -0.0000

Data Index: 520684 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 4.1908. Min Range: -4.1908

Max Act: 2.8587. Min Act: -0.0000

Data Index: 669555 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 4.1908. Min Range: -4.1908

Max Act: 3.1005. Min Act: -0.0000

Data Index: 732133 (C4 (Web Text))

Max Activating Token Index: 866

Text #13

Max Range: 4.1908. Min Range: -4.1908

Max Act: 2.8108. Min Act: -0.0000

Data Index: 440860 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 4.1908. Min Range: -4.1908

Max Act: 2.9344. Min Act: -0.0000

Data Index: 1193927 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 4.1908. Min Range: -4.1908

Max Act: 2.9097. Min Act: -0.0000

Data Index: 949534 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 4.1908. Min Range: -4.1908

Max Act: 3.0141. Min Act: -0.0000

Data Index: 18866 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 4.1908. Min Range: -4.1908

Max Act: 2.8904. Min Act: -0.0000

Data Index: 812039 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 4.1908. Min Range: -4.1908

Max Act: 2.7320. Min Act: -0.0000

Data Index: 862698 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 4.1908. Min Range: -4.1908

Max Act: 2.7315. Min Act: -0.0000

Data Index: 1044065 (C4 (Web Text))

Max Activating Token Index: 361