Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1894 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.8905. Min Range: -3.8905

Max Act: 3.8905. Min Act: -0.1700

Data Index: 339899 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 3.8905. Min Range: -3.8905

Max Act: 3.8749. Min Act: -0.1700

Data Index: 860731 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 3.8905. Min Range: -3.8905

Max Act: 3.8436. Min Act: -0.1700

Data Index: 1314734 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 3.8905. Min Range: -3.8905

Max Act: 3.8123. Min Act: -0.1700

Data Index: 1252800 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 3.8905. Min Range: -3.8905

Max Act: 3.8123. Min Act: -0.1700

Data Index: 178027 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 3.8905. Min Range: -3.8905

Max Act: 3.8280. Min Act: -0.1700

Data Index: 711073 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 3.8905. Min Range: -3.8905

Max Act: 3.8123. Min Act: -0.1700

Data Index: 621668 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 3.8905. Min Range: -3.8905

Max Act: 3.7498. Min Act: -0.1700

Data Index: 1290509 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 3.8905. Min Range: -3.8905

Max Act: 3.7967. Min Act: -0.1700

Data Index: 492694 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 3.8905. Min Range: -3.8905

Max Act: 3.8123. Min Act: -0.1700

Data Index: 158969 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 3.8905. Min Range: -3.8905

Max Act: 3.8123. Min Act: -0.1700

Data Index: 250048 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 3.8905. Min Range: -3.8905

Max Act: 3.7654. Min Act: -0.1700

Data Index: 1175414 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 3.8905. Min Range: -3.8905

Max Act: 3.7654. Min Act: -0.1700

Data Index: 630102 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 3.8905. Min Range: -3.8905

Max Act: 3.7341. Min Act: -0.1700

Data Index: 668846 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 3.8905. Min Range: -3.8905

Max Act: 3.7341. Min Act: -0.1700

Data Index: 1097970 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 3.8905. Min Range: -3.8905

Max Act: 3.7967. Min Act: -0.1700

Data Index: 67088 (C4 (Web Text))

Max Activating Token Index: 583

Text #16

Max Range: 3.8905. Min Range: -3.8905

Max Act: 3.7654. Min Act: -0.1700

Data Index: 540740 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 3.8905. Min Range: -3.8905

Max Act: 3.8123. Min Act: -0.1700

Data Index: 1251358 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 3.8905. Min Range: -3.8905

Max Act: 3.7341. Min Act: -0.1700

Data Index: 983213 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 3.8905. Min Range: -3.8905

Max Act: 3.7341. Min Act: -0.1700

Data Index: 302962 (C4 (Web Text))

Max Activating Token Index: 908