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

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

Neuron 1854 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: 4.0153. Min Range: -4.0153

Max Act: 4.0153. Min Act: -0.1700

Data Index: 374074 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 4.0153. Min Range: -4.0153

Max Act: 3.9527. Min Act: -0.1700

Data Index: 375034 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 4.0153. Min Range: -4.0153

Max Act: 3.9215. Min Act: -0.1700

Data Index: 1149127 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 4.0153. Min Range: -4.0153

Max Act: 3.8902. Min Act: -0.1700

Data Index: 1219510 (C4 (Web Text))

Max Activating Token Index: 676

Text #4

Max Range: 4.0153. Min Range: -4.0153

Max Act: 3.8277. Min Act: -0.1700

Data Index: 548459 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 4.0153. Min Range: -4.0153

Max Act: 3.7964. Min Act: -0.1700

Data Index: 693345 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 4.0153. Min Range: -4.0153

Max Act: 3.7964. Min Act: -0.1700

Data Index: 902887 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 4.0153. Min Range: -4.0153

Max Act: 3.7338. Min Act: -0.1700

Data Index: 1009781 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 4.0153. Min Range: -4.0153

Max Act: 3.7651. Min Act: -0.1700

Data Index: 769859 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 4.0153. Min Range: -4.0153

Max Act: 3.7651. Min Act: -0.1700

Data Index: 205674 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 4.0153. Min Range: -4.0153

Max Act: 3.7025. Min Act: -0.1700

Data Index: 938149 (C4 (Web Text))

Max Activating Token Index: 298

Text #11

Max Range: 4.0153. Min Range: -4.0153

Max Act: 3.7338. Min Act: -0.1700

Data Index: 453549 (C4 (Web Text))

Max Activating Token Index: 475

Text #12

Max Range: 4.0153. Min Range: -4.0153

Max Act: 3.7338. Min Act: -0.1700

Data Index: 1093537 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 4.0153. Min Range: -4.0153

Max Act: 3.6712. Min Act: -0.1700

Data Index: 230149 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 4.0153. Min Range: -4.0153

Max Act: 3.6712. Min Act: -0.1700

Data Index: 368245 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 4.0153. Min Range: -4.0153

Max Act: 3.7025. Min Act: -0.1700

Data Index: 1016641 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 4.0153. Min Range: -4.0153

Max Act: 3.7025. Min Act: -0.1700

Data Index: 1010342 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 4.0153. Min Range: -4.0153

Max Act: 3.7025. Min Act: -0.1700

Data Index: 202595 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 4.0153. Min Range: -4.0153

Max Act: 3.7025. Min Act: -0.1700

Data Index: 499523 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 4.0153. Min Range: -4.0153

Max Act: 3.6712. Min Act: -0.1700

Data Index: 604168 (C4 (Web Text))

Max Activating Token Index: 846