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

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

Neuron 5025 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2862. Min Range: -2.2862

Max Act: 2.1624. Min Act: -0.0000

Data Index: 27888 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 2.2862. Min Range: -2.2862

Max Act: 2.2862. Min Act: -0.0000

Data Index: 231638 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 2.2862. Min Range: -2.2862

Max Act: 2.0812. Min Act: -0.0000

Data Index: 663809 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 2.2862. Min Range: -2.2862

Max Act: 1.9910. Min Act: -0.0000

Data Index: 541844 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 2.2862. Min Range: -2.2862

Max Act: 2.0613. Min Act: -0.0000

Data Index: 995620 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 2.2862. Min Range: -2.2862

Max Act: 1.8557. Min Act: -0.0000

Data Index: 138409 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 2.2862. Min Range: -2.2862

Max Act: 1.9505. Min Act: -0.0000

Data Index: 438512 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 2.2862. Min Range: -2.2862

Max Act: 1.9495. Min Act: -0.0000

Data Index: 1111671 (C4 (Web Text))

Max Activating Token Index: 435

Text #8

Max Range: 2.2862. Min Range: -2.2862

Max Act: 1.8069. Min Act: -0.0000

Data Index: 1039393 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 2.2862. Min Range: -2.2862

Max Act: 1.9334. Min Act: -0.0000

Data Index: 962818 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 2.2862. Min Range: -2.2862

Max Act: 1.7784. Min Act: -0.0000

Data Index: 478415 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 2.2862. Min Range: -2.2862

Max Act: 1.8745. Min Act: -0.0000

Data Index: 309852 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 2.2862. Min Range: -2.2862

Max Act: 1.8659. Min Act: -0.0000

Data Index: 167225 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 2.2862. Min Range: -2.2862

Max Act: 1.9550. Min Act: -0.0000

Data Index: 525086 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 2.2862. Min Range: -2.2862

Max Act: 1.8450. Min Act: -0.0000

Data Index: 200237 (C4 (Web Text))

Max Activating Token Index: 590

Text #15

Max Range: 2.2862. Min Range: -2.2862

Max Act: 1.9411. Min Act: -0.0000

Data Index: 1108366 (C4 (Web Text))

Max Activating Token Index: 666

Text #16

Max Range: 2.2862. Min Range: -2.2862

Max Act: 1.9280. Min Act: -0.0000

Data Index: 1059478 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 2.2862. Min Range: -2.2862

Max Act: 1.7170. Min Act: -0.0000

Data Index: 1155842 (C4 (Web Text))

Max Activating Token Index: 634

Text #18

Max Range: 2.2862. Min Range: -2.2862

Max Act: 1.8101. Min Act: -0.0000

Data Index: 974382 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 2.2862. Min Range: -2.2862

Max Act: 1.9030. Min Act: -0.0000

Data Index: 493710 (C4 (Web Text))

Max Activating Token Index: 746