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

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

Neuron 1143 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5770. Min Range: -5.5770

Max Act: 5.5770. Min Act: -0.1700

Data Index: 475398 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 5.5770. Min Range: -5.5770

Max Act: 5.5145. Min Act: -0.1700

Data Index: 886311 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 5.5770. Min Range: -5.5770

Max Act: 5.5457. Min Act: -0.1700

Data Index: 1139692 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 5.5770. Min Range: -5.5770

Max Act: 5.4832. Min Act: -0.1700

Data Index: 86214 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 5.5770. Min Range: -5.5770

Max Act: 5.4832. Min Act: -0.1700

Data Index: 216880 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 5.5770. Min Range: -5.5770

Max Act: 5.4832. Min Act: -0.1700

Data Index: 311401 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 5.5770. Min Range: -5.5770

Max Act: 5.4207. Min Act: -0.1700

Data Index: 383695 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 5.5770. Min Range: -5.5770

Max Act: 5.4207. Min Act: -0.1700

Data Index: 923238 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 5.5770. Min Range: -5.5770

Max Act: 5.3895. Min Act: -0.1700

Data Index: 851967 (C4 (Web Text))

Max Activating Token Index: 372

Text #9

Max Range: 5.5770. Min Range: -5.5770

Max Act: 5.4520. Min Act: -0.1700

Data Index: 98909 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 5.5770. Min Range: -5.5770

Max Act: 5.3895. Min Act: -0.1700

Data Index: 634321 (C4 (Web Text))

Max Activating Token Index: 623

Text #11

Max Range: 5.5770. Min Range: -5.5770

Max Act: 5.4207. Min Act: -0.1700

Data Index: 108875 (C4 (Web Text))

Max Activating Token Index: 339

Text #12

Max Range: 5.5770. Min Range: -5.5770

Max Act: 5.4207. Min Act: -0.1700

Data Index: 314952 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 5.5770. Min Range: -5.5770

Max Act: 5.3895. Min Act: -0.1700

Data Index: 18563 (C4 (Web Text))

Max Activating Token Index: 173

Text #14

Max Range: 5.5770. Min Range: -5.5770

Max Act: 5.3582. Min Act: -0.1700

Data Index: 1249844 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 5.5770. Min Range: -5.5770

Max Act: 5.3895. Min Act: -0.1700

Data Index: 334695 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 5.5770. Min Range: -5.5770

Max Act: 5.2332. Min Act: -0.1700

Data Index: 1103790 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 5.5770. Min Range: -5.5770

Max Act: 5.2957. Min Act: -0.1700

Data Index: 24943 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 5.5770. Min Range: -5.5770

Max Act: 5.2957. Min Act: -0.1700

Data Index: 874067 (C4 (Web Text))

Max Activating Token Index: 602

Text #19

Max Range: 5.5770. Min Range: -5.5770

Max Act: 5.3270. Min Act: -0.1700

Data Index: 513200 (C4 (Web Text))

Max Activating Token Index: 791