Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1020 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.9493. Min Range: -3.9493

Max Act: 3.9493. Min Act: -0.1700

Data Index: 938362 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 3.9493. Min Range: -3.9493

Max Act: 3.9337. Min Act: -0.1700

Data Index: 672864 (C4 (Web Text))

Max Activating Token Index: 478

Text #2

Max Range: 3.9493. Min Range: -3.9493

Max Act: 3.8712. Min Act: -0.1700

Data Index: 504074 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 3.9493. Min Range: -3.9493

Max Act: 3.8712. Min Act: -0.1700

Data Index: 325192 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 3.9493. Min Range: -3.9493

Max Act: 3.8712. Min Act: -0.1700

Data Index: 970635 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 3.9493. Min Range: -3.9493

Max Act: 3.8868. Min Act: -0.1700

Data Index: 130532 (C4 (Web Text))

Max Activating Token Index: 553

Text #6

Max Range: 3.9493. Min Range: -3.9493

Max Act: 3.8243. Min Act: -0.1700

Data Index: 703497 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 3.9493. Min Range: -3.9493

Max Act: 3.8712. Min Act: -0.1700

Data Index: 393287 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 3.9493. Min Range: -3.9493

Max Act: 3.8712. Min Act: -0.1700

Data Index: 114948 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 3.9493. Min Range: -3.9493

Max Act: 3.8555. Min Act: -0.1700

Data Index: 239314 (C4 (Web Text))

Max Activating Token Index: 354

Text #10

Max Range: 3.9493. Min Range: -3.9493

Max Act: 3.7930. Min Act: -0.1700

Data Index: 53671 (C4 (Web Text))

Max Activating Token Index: 623

Text #11

Max Range: 3.9493. Min Range: -3.9493

Max Act: 3.7930. Min Act: -0.1700

Data Index: 467578 (C4 (Web Text))

Max Activating Token Index: 383

Text #12

Max Range: 3.9493. Min Range: -3.9493

Max Act: 3.7930. Min Act: -0.1700

Data Index: 777399 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 3.9493. Min Range: -3.9493

Max Act: 3.7930. Min Act: -0.1700

Data Index: 956940 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 3.9493. Min Range: -3.9493

Max Act: 3.8243. Min Act: -0.1700

Data Index: 359474 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 3.9493. Min Range: -3.9493

Max Act: 3.7617. Min Act: -0.1700

Data Index: 1338455 (C4 (Web Text))

Max Activating Token Index: 479

Text #16

Max Range: 3.9493. Min Range: -3.9493

Max Act: 3.7460. Min Act: -0.1700

Data Index: 817316 (C4 (Web Text))

Max Activating Token Index: 453

Text #17

Max Range: 3.9493. Min Range: -3.9493

Max Act: 3.7460. Min Act: -0.1700

Data Index: 420066 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 3.9493. Min Range: -3.9493

Max Act: 3.7617. Min Act: -0.1700

Data Index: 575625 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 3.9493. Min Range: -3.9493

Max Act: 3.7617. Min Act: -0.1700

Data Index: 72728 (C4 (Web Text))

Max Activating Token Index: 419