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

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

Neuron 1253 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0808. Min Range: -0.0808

Max Act: 0.0808. Min Act: -0.0000

Data Index: 295231 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 0.0808. Min Range: -0.0808

Max Act: 0.0794. Min Act: -0.0000

Data Index: 174115 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 0.0808. Min Range: -0.0808

Max Act: 0.0763. Min Act: -0.0000

Data Index: 1039203 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 0.0808. Min Range: -0.0808

Max Act: 0.0697. Min Act: -0.0000

Data Index: 1488675 (Python Code)

Max Activating Token Index: 663

Text #4

Max Range: 0.0808. Min Range: -0.0808

Max Act: 0.0704. Min Act: -0.0000

Data Index: 1298047 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 0.0808. Min Range: -0.0808

Max Act: 0.0788. Min Act: -0.0000

Data Index: 1448466 (Python Code)

Max Activating Token Index: 697

Text #6

Max Range: 0.0808. Min Range: -0.0808

Max Act: 0.0783. Min Act: -0.0000

Data Index: 370913 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 0.0808. Min Range: -0.0808

Max Act: 0.0694. Min Act: -0.0000

Data Index: 1126351 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 0.0808. Min Range: -0.0808

Max Act: 0.0687. Min Act: -0.0000

Data Index: 1106793 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 0.0808. Min Range: -0.0808

Max Act: 0.0655. Min Act: -0.0000

Data Index: 115801 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 0.0808. Min Range: -0.0808

Max Act: 0.0680. Min Act: -0.0000

Data Index: 163477 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 0.0808. Min Range: -0.0808

Max Act: 0.0604. Min Act: -0.0000

Data Index: 134479 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 0.0808. Min Range: -0.0808

Max Act: 0.0689. Min Act: -0.0000

Data Index: 426143 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 0.0808. Min Range: -0.0808

Max Act: 0.0641. Min Act: -0.0000

Data Index: 576804 (C4 (Web Text))

Max Activating Token Index: 776

Text #14

Max Range: 0.0808. Min Range: -0.0808

Max Act: 0.0568. Min Act: -0.0000

Data Index: 351938 (C4 (Web Text))

Max Activating Token Index: 415

Text #15

Max Range: 0.0808. Min Range: -0.0808

Max Act: 0.0647. Min Act: -0.0000

Data Index: 647016 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 0.0808. Min Range: -0.0808

Max Act: 0.0624. Min Act: -0.0000

Data Index: 1403545 (Python Code)

Max Activating Token Index: 415

Text #17

Max Range: 0.0808. Min Range: -0.0808

Max Act: 0.0620. Min Act: -0.0000

Data Index: 694517 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 0.0808. Min Range: -0.0808

Max Act: 0.0612. Min Act: -0.0000

Data Index: 1077315 (C4 (Web Text))

Max Activating Token Index: 453

Text #19

Max Range: 0.0808. Min Range: -0.0808

Max Act: 0.0628. Min Act: -0.0000

Data Index: 616628 (C4 (Web Text))

Max Activating Token Index: 485