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

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

Neuron 895 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7449. Min Range: -5.7449

Max Act: 5.7449. Min Act: -0.1700

Data Index: 589567 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 5.7449. Min Range: -5.7449

Max Act: 5.6199. Min Act: -0.1700

Data Index: 24844 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 5.7449. Min Range: -5.7449

Max Act: 5.5261. Min Act: -0.1700

Data Index: 783487 (C4 (Web Text))

Max Activating Token Index: 746

Text #3

Max Range: 5.7449. Min Range: -5.7449

Max Act: 5.3699. Min Act: -0.1700

Data Index: 340693 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 5.7449. Min Range: -5.7449

Max Act: 5.5574. Min Act: -0.1700

Data Index: 1275667 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 5.7449. Min Range: -5.7449

Max Act: 5.4011. Min Act: -0.1700

Data Index: 485703 (C4 (Web Text))

Max Activating Token Index: 764

Text #6

Max Range: 5.7449. Min Range: -5.7449

Max Act: 5.4949. Min Act: -0.1700

Data Index: 1129122 (C4 (Web Text))

Max Activating Token Index: 345

Text #7

Max Range: 5.7449. Min Range: -5.7449

Max Act: 5.5261. Min Act: -0.1700

Data Index: 1193582 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 5.7449. Min Range: -5.7449

Max Act: 5.4636. Min Act: -0.1700

Data Index: 1191747 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 5.7449. Min Range: -5.7449

Max Act: 5.4636. Min Act: -0.1700

Data Index: 437000 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 5.7449. Min Range: -5.7449

Max Act: 5.3386. Min Act: -0.1700

Data Index: 120485 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 5.7449. Min Range: -5.7449

Max Act: 5.4011. Min Act: -0.1700

Data Index: 1013090 (C4 (Web Text))

Max Activating Token Index: 713

Text #12

Max Range: 5.7449. Min Range: -5.7449

Max Act: 5.3074. Min Act: -0.1700

Data Index: 100760 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 5.7449. Min Range: -5.7449

Max Act: 5.4011. Min Act: -0.1700

Data Index: 735018 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 5.7449. Min Range: -5.7449

Max Act: 5.4011. Min Act: -0.1700

Data Index: 880850 (C4 (Web Text))

Max Activating Token Index: 420

Text #15

Max Range: 5.7449. Min Range: -5.7449

Max Act: 5.4949. Min Act: -0.1700

Data Index: 479490 (C4 (Web Text))

Max Activating Token Index: 380

Text #16

Max Range: 5.7449. Min Range: -5.7449

Max Act: 5.3386. Min Act: -0.1700

Data Index: 1029179 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 5.7449. Min Range: -5.7449

Max Act: 5.4011. Min Act: -0.1700

Data Index: 128601 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 5.7449. Min Range: -5.7449

Max Act: 5.3386. Min Act: -0.1700

Data Index: 1073817 (C4 (Web Text))

Max Activating Token Index: 331

Text #19

Max Range: 5.7449. Min Range: -5.7449

Max Act: 5.4324. Min Act: -0.1700

Data Index: 118285 (C4 (Web Text))

Max Activating Token Index: 77