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

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

Neuron 1121 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: 3.4857. Min Range: -3.4857

Max Act: 3.4857. Min Act: -0.1700

Data Index: 723177 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 3.4857. Min Range: -3.4857

Max Act: 3.3916. Min Act: -0.1700

Data Index: 1008661 (C4 (Web Text))

Max Activating Token Index: 901

Text #2

Max Range: 3.4857. Min Range: -3.4857

Max Act: 3.3916. Min Act: -0.1700

Data Index: 968648 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 3.4857. Min Range: -3.4857

Max Act: 3.3759. Min Act: -0.1700

Data Index: 946930 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 3.4857. Min Range: -3.4857

Max Act: 3.3916. Min Act: -0.1700

Data Index: 759796 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 3.4857. Min Range: -3.4857

Max Act: 3.3288. Min Act: -0.1700

Data Index: 983477 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 3.4857. Min Range: -3.4857

Max Act: 3.3288. Min Act: -0.1700

Data Index: 626748 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 3.4857. Min Range: -3.4857

Max Act: 3.2660. Min Act: -0.1700

Data Index: 1313895 (C4 (Web Text))

Max Activating Token Index: 568

Text #8

Max Range: 3.4857. Min Range: -3.4857

Max Act: 3.2660. Min Act: -0.1700

Data Index: 463230 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 3.4857. Min Range: -3.4857

Max Act: 3.2974. Min Act: -0.1700

Data Index: 1124931 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 3.4857. Min Range: -3.4857

Max Act: 3.2817. Min Act: -0.1700

Data Index: 1252749 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 3.4857. Min Range: -3.4857

Max Act: 3.2503. Min Act: -0.1700

Data Index: 860744 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 3.4857. Min Range: -3.4857

Max Act: 3.2346. Min Act: -0.1700

Data Index: 99388 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 3.4857. Min Range: -3.4857

Max Act: 3.2660. Min Act: -0.1700

Data Index: 591096 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 3.4857. Min Range: -3.4857

Max Act: 3.2503. Min Act: -0.1700

Data Index: 1063588 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 3.4857. Min Range: -3.4857

Max Act: 3.2817. Min Act: -0.1700

Data Index: 528953 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 3.4857. Min Range: -3.4857

Max Act: 3.2503. Min Act: -0.1700

Data Index: 187040 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 3.4857. Min Range: -3.4857

Max Act: 3.2188. Min Act: -0.1700

Data Index: 780800 (C4 (Web Text))

Max Activating Token Index: 372

Text #18

Max Range: 3.4857. Min Range: -3.4857

Max Act: 3.2031. Min Act: -0.1700

Data Index: 765474 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 3.4857. Min Range: -3.4857

Max Act: 3.2188. Min Act: -0.1700

Data Index: 721929 (C4 (Web Text))

Max Activating Token Index: 106