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

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

Neuron 1019 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: 3.3740. Min Range: -3.3740

Max Act: 3.3583. Min Act: -0.1700

Data Index: 1306263 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 3.3740. Min Range: -3.3740

Max Act: 3.3269. Min Act: -0.1700

Data Index: 1313848 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 3.3740. Min Range: -3.3740

Max Act: 3.3740. Min Act: -0.1700

Data Index: 1037123 (C4 (Web Text))

Max Activating Token Index: 480

Text #3

Max Range: 3.3740. Min Range: -3.3740

Max Act: 3.3269. Min Act: -0.1700

Data Index: 1354420 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 3.3740. Min Range: -3.3740

Max Act: 3.3269. Min Act: -0.1700

Data Index: 32145 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 3.3740. Min Range: -3.3740

Max Act: 3.3583. Min Act: -0.1700

Data Index: 1171939 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 3.3740. Min Range: -3.3740

Max Act: 3.3269. Min Act: -0.1700

Data Index: 111148 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 3.3740. Min Range: -3.3740

Max Act: 3.2798. Min Act: -0.1700

Data Index: 691203 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 3.3740. Min Range: -3.3740

Max Act: 3.2798. Min Act: -0.1700

Data Index: 686234 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 3.3740. Min Range: -3.3740

Max Act: 3.2483. Min Act: -0.1700

Data Index: 1097341 (C4 (Web Text))

Max Activating Token Index: 94

Text #10

Max Range: 3.3740. Min Range: -3.3740

Max Act: 3.2326. Min Act: -0.1700

Data Index: 1259972 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 3.3740. Min Range: -3.3740

Max Act: 3.2169. Min Act: -0.1700

Data Index: 338652 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 3.3740. Min Range: -3.3740

Max Act: 3.2326. Min Act: -0.1700

Data Index: 999710 (C4 (Web Text))

Max Activating Token Index: 63

Text #13

Max Range: 3.3740. Min Range: -3.3740

Max Act: 3.2326. Min Act: -0.1700

Data Index: 783298 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 3.3740. Min Range: -3.3740

Max Act: 3.2169. Min Act: -0.1700

Data Index: 661779 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 3.3740. Min Range: -3.3740

Max Act: 3.2169. Min Act: -0.1700

Data Index: 1064040 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 3.3740. Min Range: -3.3740

Max Act: 3.1540. Min Act: -0.1700

Data Index: 733528 (C4 (Web Text))

Max Activating Token Index: 443

Text #17

Max Range: 3.3740. Min Range: -3.3740

Max Act: 3.2798. Min Act: -0.1700

Data Index: 946752 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 3.3740. Min Range: -3.3740

Max Act: 3.1697. Min Act: -0.1700

Data Index: 1322476 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 3.3740. Min Range: -3.3740

Max Act: 3.1540. Min Act: -0.1700

Data Index: 1189309 (C4 (Web Text))

Max Activating Token Index: 922