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

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

Neuron 767 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: 3.4607. Min Range: -3.4607

Max Act: 3.4607. Min Act: -0.1700

Data Index: 772621 (C4 (Web Text))

Max Activating Token Index: 517

Text #1

Max Range: 3.4607. Min Range: -3.4607

Max Act: 3.4607. Min Act: -0.1700

Data Index: 1164492 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 3.4607. Min Range: -3.4607

Max Act: 3.4293. Min Act: -0.1700

Data Index: 803506 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 3.4607. Min Range: -3.4607

Max Act: 3.4136. Min Act: -0.1700

Data Index: 1129974 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 3.4607. Min Range: -3.4607

Max Act: 3.4136. Min Act: -0.1700

Data Index: 492479 (C4 (Web Text))

Max Activating Token Index: 482

Text #5

Max Range: 3.4607. Min Range: -3.4607

Max Act: 3.3979. Min Act: -0.1700

Data Index: 732936 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 3.4607. Min Range: -3.4607

Max Act: 3.3979. Min Act: -0.1700

Data Index: 1292414 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 3.4607. Min Range: -3.4607

Max Act: 3.2881. Min Act: -0.1700

Data Index: 945321 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 3.4607. Min Range: -3.4607

Max Act: 3.3038. Min Act: -0.1700

Data Index: 209431 (C4 (Web Text))

Max Activating Token Index: 643

Text #9

Max Range: 3.4607. Min Range: -3.4607

Max Act: 3.3195. Min Act: -0.1700

Data Index: 654305 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 3.4607. Min Range: -3.4607

Max Act: 3.3352. Min Act: -0.1700

Data Index: 174535 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 3.4607. Min Range: -3.4607

Max Act: 3.2881. Min Act: -0.1700

Data Index: 759099 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 3.4607. Min Range: -3.4607

Max Act: 3.3195. Min Act: -0.1700

Data Index: 765664 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 3.4607. Min Range: -3.4607

Max Act: 3.2881. Min Act: -0.1700

Data Index: 478085 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 3.4607. Min Range: -3.4607

Max Act: 3.3038. Min Act: -0.1700

Data Index: 1293243 (C4 (Web Text))

Max Activating Token Index: 800

Text #15

Max Range: 3.4607. Min Range: -3.4607

Max Act: 3.2723. Min Act: -0.1700

Data Index: 320384 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 3.4607. Min Range: -3.4607

Max Act: 3.2566. Min Act: -0.1700

Data Index: 129702 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 3.4607. Min Range: -3.4607

Max Act: 3.2723. Min Act: -0.1700

Data Index: 525460 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 3.4607. Min Range: -3.4607

Max Act: 3.2566. Min Act: -0.1700

Data Index: 412161 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 3.4607. Min Range: -3.4607

Max Act: 3.2566. Min Act: -0.1700

Data Index: 1263714 (C4 (Web Text))

Max Activating Token Index: 628