Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1772 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.4767. Min Act: -0.1700

Data Index: 336840 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.4924. Min Act: -0.1700

Data Index: 1017732 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.4297. Min Act: -0.1700

Data Index: 326525 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.4140. Min Act: -0.1700

Data Index: 694959 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.3983. Min Act: -0.1700

Data Index: 842900 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.3983. Min Act: -0.1700

Data Index: 677776 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.3983. Min Act: -0.1700

Data Index: 1021931 (C4 (Web Text))

Max Activating Token Index: 506

Text #7

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.3670. Min Act: -0.1700

Data Index: 1149882 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.3826. Min Act: -0.1700

Data Index: 123442 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.3983. Min Act: -0.1700

Data Index: 1299904 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.3670. Min Act: -0.1700

Data Index: 725343 (C4 (Web Text))

Max Activating Token Index: 779

Text #11

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.3670. Min Act: -0.1700

Data Index: 1007695 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.3513. Min Act: -0.1700

Data Index: 335119 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.3513. Min Act: -0.1700

Data Index: 1113719 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.3356. Min Act: -0.1700

Data Index: 367515 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.3356. Min Act: -0.1700

Data Index: 70299 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.3199. Min Act: -0.1700

Data Index: 375748 (C4 (Web Text))

Max Activating Token Index: 453

Text #17

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.3199. Min Act: -0.1700

Data Index: 1000791 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.3042. Min Act: -0.1700

Data Index: 1121810 (C4 (Web Text))

Max Activating Token Index: 475

Text #19

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.3199. Min Act: -0.1700

Data Index: 158597 (C4 (Web Text))

Max Activating Token Index: 649