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

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

Neuron 466 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.4510. Min Act: -0.0001

Data Index: 1509655 (Python Code)

Max Activating Token Index: 452

Text #1

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.4459. Min Act: -0.0001

Data Index: 1521455 (Python Code)

Max Activating Token Index: 984

Text #2

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3802. Min Act: -0.0001

Data Index: 1111731 (C4 (Web Text))

Max Activating Token Index: 897

Text #3

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3429. Min Act: -0.0001

Data Index: 1206222 (C4 (Web Text))

Max Activating Token Index: 956

Text #4

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3974. Min Act: -0.0001

Data Index: 397371 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3482. Min Act: -0.0001

Data Index: 1447131 (Python Code)

Max Activating Token Index: 540

Text #6

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3464. Min Act: -0.0001

Data Index: 1456436 (Python Code)

Max Activating Token Index: 116

Text #7

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3603. Min Act: -0.0001

Data Index: 635304 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3533. Min Act: -0.0001

Data Index: 503377 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3553. Min Act: -0.0001

Data Index: 664783 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3375. Min Act: -0.0001

Data Index: 219116 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3378. Min Act: -0.0001

Data Index: 1631851 (Python Code)

Max Activating Token Index: 462

Text #12

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3182. Min Act: -0.0001

Data Index: 1589012 (Python Code)

Max Activating Token Index: 811

Text #13

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3059. Min Act: -0.0001

Data Index: 483139 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.2791. Min Act: -0.0001

Data Index: 236262 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.2961. Min Act: -0.0001

Data Index: 607205 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3432. Min Act: -0.0001

Data Index: 1279408 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.2874. Min Act: -0.0001

Data Index: 566740 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3095. Min Act: -0.0001

Data Index: 83804 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.2919. Min Act: -0.0001

Data Index: 149160 (C4 (Web Text))

Max Activating Token Index: 636