Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 887 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.3288. Min Range: -5.3288

Max Act: 5.3288. Min Act: -0.1700

Data Index: 1189953 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 5.3288. Min Range: -5.3288

Max Act: 5.3288. Min Act: -0.1700

Data Index: 502246 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 5.3288. Min Range: -5.3288

Max Act: 5.2351. Min Act: -0.1700

Data Index: 514829 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 5.3288. Min Range: -5.3288

Max Act: 5.0163. Min Act: -0.1700

Data Index: 883748 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 5.3288. Min Range: -5.3288

Max Act: 5.1101. Min Act: -0.1700

Data Index: 251146 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 5.3288. Min Range: -5.3288

Max Act: 5.0788. Min Act: -0.1700

Data Index: 267573 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 5.3288. Min Range: -5.3288

Max Act: 5.0163. Min Act: -0.1698

Data Index: 1305119 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 5.3288. Min Range: -5.3288

Max Act: 5.0476. Min Act: -0.1700

Data Index: 1112931 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 5.3288. Min Range: -5.3288

Max Act: 5.0476. Min Act: -0.1700

Data Index: 334460 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 5.3288. Min Range: -5.3288

Max Act: 5.0788. Min Act: -0.1700

Data Index: 173922 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 5.3288. Min Range: -5.3288

Max Act: 5.0788. Min Act: -0.1700

Data Index: 1044517 (C4 (Web Text))

Max Activating Token Index: 491

Text #11

Max Range: 5.3288. Min Range: -5.3288

Max Act: 5.0476. Min Act: -0.1700

Data Index: 951850 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 5.3288. Min Range: -5.3288

Max Act: 4.9851. Min Act: -0.1700

Data Index: 746575 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 5.3288. Min Range: -5.3288

Max Act: 4.9851. Min Act: -0.1700

Data Index: 213324 (C4 (Web Text))

Max Activating Token Index: 979

Text #14

Max Range: 5.3288. Min Range: -5.3288

Max Act: 4.9538. Min Act: -0.1700

Data Index: 595125 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 5.3288. Min Range: -5.3288

Max Act: 4.9538. Min Act: -0.1700

Data Index: 293920 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 5.3288. Min Range: -5.3288

Max Act: 4.9851. Min Act: -0.1700

Data Index: 396311 (C4 (Web Text))

Max Activating Token Index: 454

Text #17

Max Range: 5.3288. Min Range: -5.3288

Max Act: 4.8601. Min Act: -0.1700

Data Index: 782368 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 5.3288. Min Range: -5.3288

Max Act: 4.9226. Min Act: -0.1700

Data Index: 1055604 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 5.3288. Min Range: -5.3288

Max Act: 4.9226. Min Act: -0.1700

Data Index: 482343 (C4 (Web Text))

Max Activating Token Index: 135