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

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

Neuron 1029 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: 5.9327. Min Range: -5.9327

Max Act: 5.9015. Min Act: -0.1700

Data Index: 247859 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 5.9327. Min Range: -5.9327

Max Act: 5.9327. Min Act: -0.1700

Data Index: 502591 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 5.9327. Min Range: -5.9327

Max Act: 5.8077. Min Act: -0.1700

Data Index: 358843 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 5.9327. Min Range: -5.9327

Max Act: 5.7452. Min Act: -0.1700

Data Index: 1164183 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 5.9327. Min Range: -5.9327

Max Act: 5.8077. Min Act: -0.1700

Data Index: 692997 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 5.9327. Min Range: -5.9327

Max Act: 5.8077. Min Act: -0.1700

Data Index: 187660 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 5.9327. Min Range: -5.9327

Max Act: 5.7140. Min Act: -0.1700

Data Index: 473172 (C4 (Web Text))

Max Activating Token Index: 986

Text #7

Max Range: 5.9327. Min Range: -5.9327

Max Act: 5.7452. Min Act: -0.1700

Data Index: 215242 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 5.9327. Min Range: -5.9327

Max Act: 5.7140. Min Act: -0.1700

Data Index: 333281 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 5.9327. Min Range: -5.9327

Max Act: 5.7140. Min Act: -0.1700

Data Index: 696821 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 5.9327. Min Range: -5.9327

Max Act: 5.7140. Min Act: -0.1700

Data Index: 472525 (C4 (Web Text))

Max Activating Token Index: 697

Text #11

Max Range: 5.9327. Min Range: -5.9327

Max Act: 5.7452. Min Act: -0.1700

Data Index: 1318237 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 5.9327. Min Range: -5.9327

Max Act: 5.7140. Min Act: -0.1700

Data Index: 1324995 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 5.9327. Min Range: -5.9327

Max Act: 5.7140. Min Act: -0.1700

Data Index: 735023 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 5.9327. Min Range: -5.9327

Max Act: 5.7140. Min Act: -0.1700

Data Index: 974330 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 5.9327. Min Range: -5.9327

Max Act: 5.7140. Min Act: -0.1700

Data Index: 827772 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 5.9327. Min Range: -5.9327

Max Act: 5.6515. Min Act: -0.1700

Data Index: 635171 (C4 (Web Text))

Max Activating Token Index: 685

Text #17

Max Range: 5.9327. Min Range: -5.9327

Max Act: 5.6515. Min Act: -0.1700

Data Index: 526753 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 5.9327. Min Range: -5.9327

Max Act: 5.7140. Min Act: -0.1700

Data Index: 954637 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 5.9327. Min Range: -5.9327

Max Act: 5.7140. Min Act: -0.1700

Data Index: 203674 (C4 (Web Text))

Max Activating Token Index: 486