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

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

Neuron 6056 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1862. Min Range: -2.1862

Max Act: 2.1132. Min Act: -0.0000

Data Index: 1325662 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 2.1862. Min Range: -2.1862

Max Act: 2.0093. Min Act: -0.0000

Data Index: 289997 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 2.1862. Min Range: -2.1862

Max Act: 2.1862. Min Act: -0.0000

Data Index: 1115236 (C4 (Web Text))

Max Activating Token Index: 337

Text #3

Max Range: 2.1862. Min Range: -2.1862

Max Act: 1.7817. Min Act: -0.0000

Data Index: 1011000 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 2.1862. Min Range: -2.1862

Max Act: 1.7683. Min Act: -0.0000

Data Index: 1132232 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 2.1862. Min Range: -2.1862

Max Act: 1.4711. Min Act: -0.0000

Data Index: 590981 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 2.1862. Min Range: -2.1862

Max Act: 1.5806. Min Act: -0.0000

Data Index: 884200 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 2.1862. Min Range: -2.1862

Max Act: 1.5715. Min Act: -0.0000

Data Index: 731962 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 2.1862. Min Range: -2.1862

Max Act: 1.4717. Min Act: -0.0000

Data Index: 995250 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 2.1862. Min Range: -2.1862

Max Act: 1.2796. Min Act: -0.0000

Data Index: 345021 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 2.1862. Min Range: -2.1862

Max Act: 1.3458. Min Act: -0.0000

Data Index: 447047 (C4 (Web Text))

Max Activating Token Index: 346

Text #11

Max Range: 2.1862. Min Range: -2.1862

Max Act: 1.3053. Min Act: -0.0000

Data Index: 430295 (C4 (Web Text))

Max Activating Token Index: 251

Text #12

Max Range: 2.1862. Min Range: -2.1862

Max Act: 1.3318. Min Act: -0.0000

Data Index: 1136194 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 2.1862. Min Range: -2.1862

Max Act: 1.2034. Min Act: -0.0000

Data Index: 1530557 (Python Code)

Max Activating Token Index: 148

Text #14

Max Range: 2.1862. Min Range: -2.1862

Max Act: 1.0697. Min Act: -0.0000

Data Index: 396080 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 2.1862. Min Range: -2.1862

Max Act: 1.1890. Min Act: -0.0000

Data Index: 200057 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 2.1862. Min Range: -2.1862

Max Act: 1.0027. Min Act: -0.0000

Data Index: 325855 (C4 (Web Text))

Max Activating Token Index: 279

Text #17

Max Range: 2.1862. Min Range: -2.1862

Max Act: 1.0666. Min Act: -0.0000

Data Index: 970990 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 2.1862. Min Range: -2.1862

Max Act: 1.0619. Min Act: -0.0000

Data Index: 832619 (C4 (Web Text))

Max Activating Token Index: 333

Text #19

Max Range: 2.1862. Min Range: -2.1862

Max Act: 0.8784. Min Act: -0.0000

Data Index: 1087745 (C4 (Web Text))

Max Activating Token Index: 267