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

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

Neuron 378 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: 4.7102. Min Range: -4.7102

Max Act: 4.7102. Min Act: -0.0000

Data Index: 807193 (C4 (Web Text))

Max Activating Token Index: 1010

Text #1

Max Range: 4.7102. Min Range: -4.7102

Max Act: 4.2709. Min Act: -0.0000

Data Index: 172619 (C4 (Web Text))

Max Activating Token Index: 276

Text #2

Max Range: 4.7102. Min Range: -4.7102

Max Act: 4.2911. Min Act: -0.0000

Data Index: 412273 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 4.7102. Min Range: -4.7102

Max Act: 4.2670. Min Act: -0.0000

Data Index: 115069 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 4.7102. Min Range: -4.7102

Max Act: 4.0371. Min Act: -0.0000

Data Index: 1016910 (C4 (Web Text))

Max Activating Token Index: 468

Text #5

Max Range: 4.7102. Min Range: -4.7102

Max Act: 4.2086. Min Act: -0.0000

Data Index: 1275587 (C4 (Web Text))

Max Activating Token Index: 552

Text #6

Max Range: 4.7102. Min Range: -4.7102

Max Act: 4.0841. Min Act: -0.0000

Data Index: 808298 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 4.7102. Min Range: -4.7102

Max Act: 3.9176. Min Act: -0.0000

Data Index: 1353636 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 4.7102. Min Range: -4.7102

Max Act: 3.8775. Min Act: -0.0000

Data Index: 1014503 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 4.7102. Min Range: -4.7102

Max Act: 3.8611. Min Act: -0.0000

Data Index: 717473 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 4.7102. Min Range: -4.7102

Max Act: 3.9423. Min Act: -0.0000

Data Index: 140018 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 4.7102. Min Range: -4.7102

Max Act: 3.7769. Min Act: -0.0000

Data Index: 652948 (C4 (Web Text))

Max Activating Token Index: 617

Text #12

Max Range: 4.7102. Min Range: -4.7102

Max Act: 3.9309. Min Act: -0.0000

Data Index: 883693 (C4 (Web Text))

Max Activating Token Index: 833

Text #13

Max Range: 4.7102. Min Range: -4.7102

Max Act: 3.8990. Min Act: -0.0000

Data Index: 728262 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 4.7102. Min Range: -4.7102

Max Act: 3.8688. Min Act: -0.0000

Data Index: 1003830 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 4.7102. Min Range: -4.7102

Max Act: 3.8542. Min Act: -0.0000

Data Index: 834310 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 4.7102. Min Range: -4.7102

Max Act: 3.7358. Min Act: -0.0000

Data Index: 536135 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 4.7102. Min Range: -4.7102

Max Act: 3.8268. Min Act: -0.0000

Data Index: 1347033 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 4.7102. Min Range: -4.7102

Max Act: 3.8119. Min Act: -0.0000

Data Index: 1242328 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 4.7102. Min Range: -4.7102

Max Act: 3.8034. Min Act: -0.0000

Data Index: 424670 (C4 (Web Text))

Max Activating Token Index: 632