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

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

Neuron 468 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6315. Min Range: -5.6315

Max Act: 5.6315. Min Act: -0.1700

Data Index: 681089 (C4 (Web Text))

Max Activating Token Index: 732

Text #1

Max Range: 5.6315. Min Range: -5.6315

Max Act: 5.4440. Min Act: -0.1700

Data Index: 1031475 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 5.6315. Min Range: -5.6315

Max Act: 5.4753. Min Act: -0.1700

Data Index: 824239 (C4 (Web Text))

Max Activating Token Index: 448

Text #3

Max Range: 5.6315. Min Range: -5.6315

Max Act: 5.3815. Min Act: -0.1700

Data Index: 7860 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 5.6315. Min Range: -5.6315

Max Act: 5.4128. Min Act: -0.1700

Data Index: 62302 (C4 (Web Text))

Max Activating Token Index: 359

Text #5

Max Range: 5.6315. Min Range: -5.6315

Max Act: 5.3815. Min Act: -0.1700

Data Index: 796491 (C4 (Web Text))

Max Activating Token Index: 674

Text #6

Max Range: 5.6315. Min Range: -5.6315

Max Act: 5.3190. Min Act: -0.1700

Data Index: 371267 (C4 (Web Text))

Max Activating Token Index: 430

Text #7

Max Range: 5.6315. Min Range: -5.6315

Max Act: 5.3190. Min Act: -0.1700

Data Index: 1260114 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 5.6315. Min Range: -5.6315

Max Act: 5.2878. Min Act: -0.1700

Data Index: 607205 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 5.6315. Min Range: -5.6315

Max Act: 5.3503. Min Act: -0.1700

Data Index: 1213427 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 5.6315. Min Range: -5.6315

Max Act: 5.2253. Min Act: -0.1700

Data Index: 892972 (C4 (Web Text))

Max Activating Token Index: 697

Text #11

Max Range: 5.6315. Min Range: -5.6315

Max Act: 5.2878. Min Act: -0.1700

Data Index: 123075 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 5.6315. Min Range: -5.6315

Max Act: 5.2878. Min Act: -0.1700

Data Index: 614957 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 5.6315. Min Range: -5.6315

Max Act: 5.2878. Min Act: -0.1700

Data Index: 126155 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 5.6315. Min Range: -5.6315

Max Act: 5.2253. Min Act: -0.1700

Data Index: 72706 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 5.6315. Min Range: -5.6315

Max Act: 5.2253. Min Act: -0.1700

Data Index: 710836 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 5.6315. Min Range: -5.6315

Max Act: 5.1940. Min Act: -0.1700

Data Index: 498254 (C4 (Web Text))

Max Activating Token Index: 598

Text #17

Max Range: 5.6315. Min Range: -5.6315

Max Act: 5.1940. Min Act: -0.1700

Data Index: 883557 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 5.6315. Min Range: -5.6315

Max Act: 5.1628. Min Act: -0.1700

Data Index: 1349776 (C4 (Web Text))

Max Activating Token Index: 983

Text #19

Max Range: 5.6315. Min Range: -5.6315

Max Act: 5.1940. Min Act: -0.1700

Data Index: 354286 (C4 (Web Text))

Max Activating Token Index: 317