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

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

Neuron 1544 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2118. Min Range: -3.2118

Max Act: 3.2118. Min Act: -0.1700

Data Index: 1248689 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 3.2118. Min Range: -3.2118

Max Act: 3.1961. Min Act: -0.1700

Data Index: 1071808 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 3.2118. Min Range: -3.2118

Max Act: 3.1174. Min Act: -0.1700

Data Index: 49604 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 3.2118. Min Range: -3.2118

Max Act: 3.0701. Min Act: -0.1700

Data Index: 351465 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 3.2118. Min Range: -3.2118

Max Act: 3.0543. Min Act: -0.1700

Data Index: 1104611 (C4 (Web Text))

Max Activating Token Index: 438

Text #5

Max Range: 3.2118. Min Range: -3.2118

Max Act: 3.0701. Min Act: -0.1700

Data Index: 1124155 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 3.2118. Min Range: -3.2118

Max Act: 3.0227. Min Act: -0.1700

Data Index: 1191947 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 3.2118. Min Range: -3.2118

Max Act: 3.0227. Min Act: -0.1700

Data Index: 344048 (C4 (Web Text))

Max Activating Token Index: 843

Text #8

Max Range: 3.2118. Min Range: -3.2118

Max Act: 2.9911. Min Act: -0.1700

Data Index: 910172 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 3.2118. Min Range: -3.2118

Max Act: 3.0069. Min Act: -0.1700

Data Index: 1148481 (C4 (Web Text))

Max Activating Token Index: 405

Text #10

Max Range: 3.2118. Min Range: -3.2118

Max Act: 2.9753. Min Act: -0.1700

Data Index: 809482 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 3.2118. Min Range: -3.2118

Max Act: 2.9594. Min Act: -0.1700

Data Index: 259574 (C4 (Web Text))

Max Activating Token Index: 934

Text #12

Max Range: 3.2118. Min Range: -3.2118

Max Act: 2.9911. Min Act: -0.1700

Data Index: 1153731 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 3.2118. Min Range: -3.2118

Max Act: 3.0227. Min Act: -0.1700

Data Index: 1028501 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 3.2118. Min Range: -3.2118

Max Act: 2.9594. Min Act: -0.1700

Data Index: 283311 (C4 (Web Text))

Max Activating Token Index: 516

Text #15

Max Range: 3.2118. Min Range: -3.2118

Max Act: 2.9436. Min Act: -0.1700

Data Index: 129623 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 3.2118. Min Range: -3.2118

Max Act: 2.9278. Min Act: -0.1700

Data Index: 391804 (C4 (Web Text))

Max Activating Token Index: 511

Text #17

Max Range: 3.2118. Min Range: -3.2118

Max Act: 2.9436. Min Act: -0.1700

Data Index: 190341 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 3.2118. Min Range: -3.2118

Max Act: 2.8802. Min Act: -0.1700

Data Index: 873563 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 3.2118. Min Range: -3.2118

Max Act: 2.8961. Min Act: -0.1700

Data Index: 1174094 (C4 (Web Text))

Max Activating Token Index: 26