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

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

Neuron 1162 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: 5.7581. Min Range: -5.7581

Max Act: 5.7269. Min Act: -0.1700

Data Index: 1316494 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 5.7581. Min Range: -5.7581

Max Act: 5.5706. Min Act: -0.1700

Data Index: 486541 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 5.7581. Min Range: -5.7581

Max Act: 5.7581. Min Act: -0.1700

Data Index: 843530 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 5.7581. Min Range: -5.7581

Max Act: 5.5706. Min Act: -0.1700

Data Index: 1078892 (C4 (Web Text))

Max Activating Token Index: 949

Text #4

Max Range: 5.7581. Min Range: -5.7581

Max Act: 5.5394. Min Act: -0.1700

Data Index: 333073 (C4 (Web Text))

Max Activating Token Index: 482

Text #5

Max Range: 5.7581. Min Range: -5.7581

Max Act: 5.4144. Min Act: -0.1700

Data Index: 1003233 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 5.7581. Min Range: -5.7581

Max Act: 5.4456. Min Act: -0.1700

Data Index: 866504 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 5.7581. Min Range: -5.7581

Max Act: 5.3519. Min Act: -0.1700

Data Index: 924534 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 5.7581. Min Range: -5.7581

Max Act: 5.3519. Min Act: -0.1700

Data Index: 247305 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 5.7581. Min Range: -5.7581

Max Act: 5.3831. Min Act: -0.1700

Data Index: 484817 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 5.7581. Min Range: -5.7581

Max Act: 5.3831. Min Act: -0.1700

Data Index: 724606 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 5.7581. Min Range: -5.7581

Max Act: 5.3519. Min Act: -0.1700

Data Index: 1357581 (C4 (Web Text))

Max Activating Token Index: 934

Text #12

Max Range: 5.7581. Min Range: -5.7581

Max Act: 5.2894. Min Act: -0.1700

Data Index: 426701 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 5.7581. Min Range: -5.7581

Max Act: 5.2894. Min Act: -0.1700

Data Index: 1147268 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 5.7581. Min Range: -5.7581

Max Act: 5.3206. Min Act: -0.1700

Data Index: 433641 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 5.7581. Min Range: -5.7581

Max Act: 5.3206. Min Act: -0.1700

Data Index: 105735 (C4 (Web Text))

Max Activating Token Index: 435

Text #16

Max Range: 5.7581. Min Range: -5.7581

Max Act: 5.2269. Min Act: -0.1700

Data Index: 336962 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 5.7581. Min Range: -5.7581

Max Act: 5.3519. Min Act: -0.1700

Data Index: 846507 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 5.7581. Min Range: -5.7581

Max Act: 5.2269. Min Act: -0.1700

Data Index: 1068406 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 5.7581. Min Range: -5.7581

Max Act: 5.3519. Min Act: -0.1700

Data Index: 526065 (C4 (Web Text))

Max Activating Token Index: 827