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

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

Neuron 1643 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: 3.6833. Min Range: -3.6833

Max Act: 3.6833. Min Act: -0.1700

Data Index: 735546 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 3.6833. Min Range: -3.6833

Max Act: 3.4994. Min Act: -0.1700

Data Index: 618347 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 3.6833. Min Range: -3.6833

Max Act: 3.5041. Min Act: -0.1700

Data Index: 166459 (C4 (Web Text))

Max Activating Token Index: 385

Text #3

Max Range: 3.6833. Min Range: -3.6833

Max Act: 3.4967. Min Act: -0.1700

Data Index: 962286 (C4 (Web Text))

Max Activating Token Index: 977

Text #4

Max Range: 3.6833. Min Range: -3.6833

Max Act: 3.4798. Min Act: -0.1700

Data Index: 629592 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 3.6833. Min Range: -3.6833

Max Act: 3.4335. Min Act: -0.1700

Data Index: 320576 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 3.6833. Min Range: -3.6833

Max Act: 3.4370. Min Act: -0.1700

Data Index: 947828 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 3.6833. Min Range: -3.6833

Max Act: 3.4122. Min Act: -0.1700

Data Index: 181687 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 3.6833. Min Range: -3.6833

Max Act: 3.4058. Min Act: -0.1700

Data Index: 1057229 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 3.6833. Min Range: -3.6833

Max Act: 3.4011. Min Act: -0.1700

Data Index: 565819 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 3.6833. Min Range: -3.6833

Max Act: 3.4016. Min Act: -0.1700

Data Index: 565447 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 3.6833. Min Range: -3.6833

Max Act: 3.3791. Min Act: -0.1700

Data Index: 18263 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 3.6833. Min Range: -3.6833

Max Act: 3.3969. Min Act: -0.1700

Data Index: 911238 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 3.6833. Min Range: -3.6833

Max Act: 3.3681. Min Act: -0.1700

Data Index: 124947 (C4 (Web Text))

Max Activating Token Index: 468

Text #14

Max Range: 3.6833. Min Range: -3.6833

Max Act: 3.3475. Min Act: -0.1700

Data Index: 1128577 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 3.6833. Min Range: -3.6833

Max Act: 3.3422. Min Act: -0.1700

Data Index: 855280 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 3.6833. Min Range: -3.6833

Max Act: 3.3257. Min Act: -0.1700

Data Index: 200359 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 3.6833. Min Range: -3.6833

Max Act: 3.3097. Min Act: -0.1700

Data Index: 251538 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 3.6833. Min Range: -3.6833

Max Act: 3.3164. Min Act: -0.1700

Data Index: 750245 (C4 (Web Text))

Max Activating Token Index: 1015

Text #19

Max Range: 3.6833. Min Range: -3.6833

Max Act: 3.3070. Min Act: -0.1700

Data Index: 837288 (C4 (Web Text))

Max Activating Token Index: 175