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

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

Neuron 1447 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: 3.2750. Min Range: -3.2750

Max Act: 3.2750. Min Act: -0.1700

Data Index: 410461 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 3.2750. Min Range: -3.2750

Max Act: 3.1492. Min Act: -0.1700

Data Index: 255819 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 3.2750. Min Range: -3.2750

Max Act: 3.1334. Min Act: -0.1700

Data Index: 71521 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 3.2750. Min Range: -3.2750

Max Act: 3.0703. Min Act: -0.1700

Data Index: 650941 (C4 (Web Text))

Max Activating Token Index: 528

Text #4

Max Range: 3.2750. Min Range: -3.2750

Max Act: 3.1176. Min Act: -0.1700

Data Index: 684204 (C4 (Web Text))

Max Activating Token Index: 469

Text #5

Max Range: 3.2750. Min Range: -3.2750

Max Act: 3.0388. Min Act: -0.1700

Data Index: 498991 (C4 (Web Text))

Max Activating Token Index: 533

Text #6

Max Range: 3.2750. Min Range: -3.2750

Max Act: 3.0703. Min Act: -0.1700

Data Index: 525003 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 3.2750. Min Range: -3.2750

Max Act: 3.0072. Min Act: -0.1700

Data Index: 833584 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 3.2750. Min Range: -3.2750

Max Act: 2.9914. Min Act: -0.1700

Data Index: 1443545 (Python Code)

Max Activating Token Index: 68

Text #9

Max Range: 3.2750. Min Range: -3.2750

Max Act: 3.0230. Min Act: -0.1700

Data Index: 1121321 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 3.2750. Min Range: -3.2750

Max Act: 3.0072. Min Act: -0.1700

Data Index: 971775 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 3.2750. Min Range: -3.2750

Max Act: 2.9914. Min Act: -0.1700

Data Index: 135776 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 3.2750. Min Range: -3.2750

Max Act: 3.0072. Min Act: -0.1700

Data Index: 563435 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 3.2750. Min Range: -3.2750

Max Act: 2.9597. Min Act: -0.1700

Data Index: 1007426 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 3.2750. Min Range: -3.2750

Max Act: 2.9597. Min Act: -0.1700

Data Index: 479583 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 3.2750. Min Range: -3.2750

Max Act: 2.9280. Min Act: -0.1700

Data Index: 1170982 (C4 (Web Text))

Max Activating Token Index: 288

Text #16

Max Range: 3.2750. Min Range: -3.2750

Max Act: 2.9755. Min Act: -0.1700

Data Index: 1267794 (C4 (Web Text))

Max Activating Token Index: 409

Text #17

Max Range: 3.2750. Min Range: -3.2750

Max Act: 2.9597. Min Act: -0.1700

Data Index: 957005 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 3.2750. Min Range: -3.2750

Max Act: 2.9280. Min Act: -0.1700

Data Index: 626955 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 3.2750. Min Range: -3.2750

Max Act: 2.9122. Min Act: -0.1700

Data Index: 874206 (C4 (Web Text))

Max Activating Token Index: 818