Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1656 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.8359. Min Range: -4.8359

Max Act: 4.8161. Min Act: -0.1700

Data Index: 970719 (C4 (Web Text))

Max Activating Token Index: 789

Text #1

Max Range: 4.8359. Min Range: -4.8359

Max Act: 4.8359. Min Act: -0.1700

Data Index: 676711 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 4.8359. Min Range: -4.8359

Max Act: 4.7588. Min Act: -0.1700

Data Index: 1282746 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 4.8359. Min Range: -4.8359

Max Act: 4.7345. Min Act: -0.1700

Data Index: 27788 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 4.8359. Min Range: -4.8359

Max Act: 4.7306. Min Act: -0.1700

Data Index: 369894 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 4.8359. Min Range: -4.8359

Max Act: 4.7190. Min Act: -0.1700

Data Index: 58132 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 4.8359. Min Range: -4.8359

Max Act: 4.6843. Min Act: -0.1700

Data Index: 1243396 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 4.8359. Min Range: -4.8359

Max Act: 4.7097. Min Act: -0.1700

Data Index: 757460 (C4 (Web Text))

Max Activating Token Index: 719

Text #8

Max Range: 4.8359. Min Range: -4.8359

Max Act: 4.7224. Min Act: -0.1700

Data Index: 1274121 (C4 (Web Text))

Max Activating Token Index: 410

Text #9

Max Range: 4.8359. Min Range: -4.8359

Max Act: 4.6460. Min Act: -0.1700

Data Index: 400822 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 4.8359. Min Range: -4.8359

Max Act: 4.6790. Min Act: -0.1700

Data Index: 1159602 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 4.8359. Min Range: -4.8359

Max Act: 4.6731. Min Act: -0.1700

Data Index: 264990 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 4.8359. Min Range: -4.8359

Max Act: 4.6771. Min Act: -0.1700

Data Index: 494224 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 4.8359. Min Range: -4.8359

Max Act: 4.6622. Min Act: -0.1700

Data Index: 375458 (C4 (Web Text))

Max Activating Token Index: 352

Text #14

Max Range: 4.8359. Min Range: -4.8359

Max Act: 4.6761. Min Act: -0.1700

Data Index: 1182718 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 4.8359. Min Range: -4.8359

Max Act: 4.6778. Min Act: -0.1700

Data Index: 237165 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 4.8359. Min Range: -4.8359

Max Act: 4.6524. Min Act: -0.1700

Data Index: 897244 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 4.8359. Min Range: -4.8359

Max Act: 4.6437. Min Act: -0.1700

Data Index: 218068 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 4.8359. Min Range: -4.8359

Max Act: 4.6123. Min Act: -0.1700

Data Index: 822945 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 4.8359. Min Range: -4.8359

Max Act: 4.6276. Min Act: -0.1700

Data Index: 373877 (C4 (Web Text))

Max Activating Token Index: 674