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

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

Neuron 1564 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.5576. Min Range: -3.5576

Max Act: 3.5576. Min Act: -0.1700

Data Index: 526147 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 3.5576. Min Range: -3.5576

Max Act: 3.4479. Min Act: -0.1700

Data Index: 1317051 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 3.5576. Min Range: -3.5576

Max Act: 3.4792. Min Act: -0.1700

Data Index: 677347 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 3.5576. Min Range: -3.5576

Max Act: 3.4949. Min Act: -0.1700

Data Index: 924222 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 3.5576. Min Range: -3.5576

Max Act: 3.4949. Min Act: -0.1700

Data Index: 1015697 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 3.5576. Min Range: -3.5576

Max Act: 3.4636. Min Act: -0.1700

Data Index: 568433 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 3.5576. Min Range: -3.5576

Max Act: 3.4636. Min Act: -0.1700

Data Index: 320045 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 3.5576. Min Range: -3.5576

Max Act: 3.4479. Min Act: -0.1700

Data Index: 305631 (C4 (Web Text))

Max Activating Token Index: 450

Text #8

Max Range: 3.5576. Min Range: -3.5576

Max Act: 3.4636. Min Act: -0.1700

Data Index: 28707 (C4 (Web Text))

Max Activating Token Index: 675

Text #9

Max Range: 3.5576. Min Range: -3.5576

Max Act: 3.4949. Min Act: -0.1700

Data Index: 247599 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 3.5576. Min Range: -3.5576

Max Act: 3.3695. Min Act: -0.1700

Data Index: 806477 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 3.5576. Min Range: -3.5576

Max Act: 3.4165. Min Act: -0.1700

Data Index: 1241498 (C4 (Web Text))

Max Activating Token Index: 484

Text #12

Max Range: 3.5576. Min Range: -3.5576

Max Act: 3.4165. Min Act: -0.1700

Data Index: 537597 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 3.5576. Min Range: -3.5576

Max Act: 3.4165. Min Act: -0.1700

Data Index: 219198 (C4 (Web Text))

Max Activating Token Index: 940

Text #14

Max Range: 3.5576. Min Range: -3.5576

Max Act: 3.4322. Min Act: -0.1700

Data Index: 764755 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 3.5576. Min Range: -3.5576

Max Act: 3.3852. Min Act: -0.1700

Data Index: 1235792 (C4 (Web Text))

Max Activating Token Index: 663

Text #16

Max Range: 3.5576. Min Range: -3.5576

Max Act: 3.4322. Min Act: -0.1700

Data Index: 220120 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 3.5576. Min Range: -3.5576

Max Act: 3.4008. Min Act: -0.1700

Data Index: 281402 (C4 (Web Text))

Max Activating Token Index: 419

Text #18

Max Range: 3.5576. Min Range: -3.5576

Max Act: 3.3852. Min Act: -0.1700

Data Index: 1109869 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 3.5576. Min Range: -3.5576

Max Act: 3.4008. Min Act: -0.1700

Data Index: 561622 (C4 (Web Text))

Max Activating Token Index: 820