Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1452 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.9400. Min Act: -0.0003

Data Index: 1055260 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.8978. Min Act: -0.0003

Data Index: 209204 (C4 (Web Text))

Max Activating Token Index: 1005

Text #2

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.8961. Min Act: -0.0003

Data Index: 633205 (C4 (Web Text))

Max Activating Token Index: 540

Text #3

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.8838. Min Act: -0.0003

Data Index: 1331496 (C4 (Web Text))

Max Activating Token Index: 164

Text #4

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.7674. Min Act: -0.0003

Data Index: 156243 (C4 (Web Text))

Max Activating Token Index: 617

Text #5

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.8742. Min Act: -0.0003

Data Index: 140475 (C4 (Web Text))

Max Activating Token Index: 834

Text #6

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.8381. Min Act: -0.0003

Data Index: 869259 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.7592. Min Act: -0.0003

Data Index: 1001884 (C4 (Web Text))

Max Activating Token Index: 547

Text #8

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.8814. Min Act: -0.0003

Data Index: 642589 (C4 (Web Text))

Max Activating Token Index: 872

Text #9

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.8477. Min Act: -0.0003

Data Index: 1073403 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.6082. Min Act: -0.0003

Data Index: 579420 (C4 (Web Text))

Max Activating Token Index: 854

Text #11

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.8469. Min Act: -0.0003

Data Index: 943361 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.7972. Min Act: -0.0003

Data Index: 1053266 (C4 (Web Text))

Max Activating Token Index: 390

Text #13

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.6680. Min Act: -0.0003

Data Index: 816620 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.8044. Min Act: -0.0003

Data Index: 1358501 (C4 (Web Text))

Max Activating Token Index: 393

Text #15

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.7814. Min Act: -0.0003

Data Index: 1031902 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.7507. Min Act: -0.0003

Data Index: 84433 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.7761. Min Act: -0.0003

Data Index: 1219842 (C4 (Web Text))

Max Activating Token Index: 487

Text #18

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.8707. Min Act: -0.0003

Data Index: 440423 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.6251. Min Act: -0.0003

Data Index: 715747 (C4 (Web Text))

Max Activating Token Index: 324