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

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

Neuron 991 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.3600. Min Range: -3.3600

Max Act: 3.3600. Min Act: -0.1700

Data Index: 1241774 (C4 (Web Text))

Max Activating Token Index: 407

Text #1

Max Range: 3.3600. Min Range: -3.3600

Max Act: 3.3286. Min Act: -0.1700

Data Index: 11313 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 3.3600. Min Range: -3.3600

Max Act: 3.3129. Min Act: -0.1700

Data Index: 504697 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 3.3600. Min Range: -3.3600

Max Act: 3.3129. Min Act: -0.1700

Data Index: 427763 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 3.3600. Min Range: -3.3600

Max Act: 3.2972. Min Act: -0.1700

Data Index: 1354427 (C4 (Web Text))

Max Activating Token Index: 361

Text #5

Max Range: 3.3600. Min Range: -3.3600

Max Act: 3.3286. Min Act: -0.1700

Data Index: 849048 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 3.3600. Min Range: -3.3600

Max Act: 3.3129. Min Act: -0.1700

Data Index: 1094295 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 3.3600. Min Range: -3.3600

Max Act: 3.3286. Min Act: -0.1700

Data Index: 430951 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 3.3600. Min Range: -3.3600

Max Act: 3.2972. Min Act: -0.1700

Data Index: 766553 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 3.3600. Min Range: -3.3600

Max Act: 3.2972. Min Act: -0.1700

Data Index: 786101 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 3.3600. Min Range: -3.3600

Max Act: 3.2815. Min Act: -0.1700

Data Index: 73334 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 3.3600. Min Range: -3.3600

Max Act: 3.2815. Min Act: -0.1700

Data Index: 109411 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 3.3600. Min Range: -3.3600

Max Act: 3.2815. Min Act: -0.1700

Data Index: 566130 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 3.3600. Min Range: -3.3600

Max Act: 3.2972. Min Act: -0.1700

Data Index: 611845 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 3.3600. Min Range: -3.3600

Max Act: 3.2972. Min Act: -0.1700

Data Index: 504067 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 3.3600. Min Range: -3.3600

Max Act: 3.2815. Min Act: -0.1700

Data Index: 272821 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 3.3600. Min Range: -3.3600

Max Act: 3.2658. Min Act: -0.1700

Data Index: 224541 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 3.3600. Min Range: -3.3600

Max Act: 3.2815. Min Act: -0.1700

Data Index: 878667 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 3.3600. Min Range: -3.3600

Max Act: 3.2658. Min Act: -0.1700

Data Index: 736506 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 3.3600. Min Range: -3.3600

Max Act: 3.2500. Min Act: -0.1700

Data Index: 153058 (C4 (Web Text))

Max Activating Token Index: 134