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

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

Neuron 1214 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8483. Min Range: -3.8483

Max Act: 3.8483. Min Act: -0.1700

Data Index: 1029287 (C4 (Web Text))

Max Activating Token Index: 898

Text #1

Max Range: 3.8483. Min Range: -3.8483

Max Act: 3.7857. Min Act: -0.1700

Data Index: 289455 (C4 (Web Text))

Max Activating Token Index: 676

Text #2

Max Range: 3.8483. Min Range: -3.8483

Max Act: 3.8170. Min Act: -0.1700

Data Index: 615172 (C4 (Web Text))

Max Activating Token Index: 840

Text #3

Max Range: 3.8483. Min Range: -3.8483

Max Act: 3.7544. Min Act: -0.1700

Data Index: 1248073 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 3.8483. Min Range: -3.8483

Max Act: 3.7544. Min Act: -0.1700

Data Index: 1155813 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 3.8483. Min Range: -3.8483

Max Act: 3.7232. Min Act: -0.1700

Data Index: 555226 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 3.8483. Min Range: -3.8483

Max Act: 3.6606. Min Act: -0.1700

Data Index: 1019355 (C4 (Web Text))

Max Activating Token Index: 1013

Text #7

Max Range: 3.8483. Min Range: -3.8483

Max Act: 3.6606. Min Act: -0.1700

Data Index: 234240 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 3.8483. Min Range: -3.8483

Max Act: 3.6919. Min Act: -0.1700

Data Index: 518137 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 3.8483. Min Range: -3.8483

Max Act: 3.6919. Min Act: -0.1700

Data Index: 400781 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 3.8483. Min Range: -3.8483

Max Act: 3.6606. Min Act: -0.1700

Data Index: 37621 (C4 (Web Text))

Max Activating Token Index: 887

Text #11

Max Range: 3.8483. Min Range: -3.8483

Max Act: 3.6293. Min Act: -0.1700

Data Index: 554116 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 3.8483. Min Range: -3.8483

Max Act: 3.6293. Min Act: -0.1700

Data Index: 1279643 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 3.8483. Min Range: -3.8483

Max Act: 3.6606. Min Act: -0.1700

Data Index: 9790 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 3.8483. Min Range: -3.8483

Max Act: 3.6606. Min Act: -0.1700

Data Index: 1287932 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 3.8483. Min Range: -3.8483

Max Act: 3.5979. Min Act: -0.1700

Data Index: 292168 (C4 (Web Text))

Max Activating Token Index: 766

Text #16

Max Range: 3.8483. Min Range: -3.8483

Max Act: 3.6606. Min Act: -0.1700

Data Index: 1267111 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 3.8483. Min Range: -3.8483

Max Act: 3.6293. Min Act: -0.1700

Data Index: 1194251 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 3.8483. Min Range: -3.8483

Max Act: 3.5979. Min Act: -0.1700

Data Index: 495545 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 3.8483. Min Range: -3.8483

Max Act: 3.6606. Min Act: -0.1700

Data Index: 194394 (C4 (Web Text))

Max Activating Token Index: 694