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

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

Neuron 1598 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: 3.9768. Min Range: -3.9768

Max Act: 3.9768. Min Act: -0.1700

Data Index: 506599 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 3.9768. Min Range: -3.9768

Max Act: 3.9142. Min Act: -0.1700

Data Index: 1317928 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 3.9768. Min Range: -3.9768

Max Act: 3.8830. Min Act: -0.1700

Data Index: 1199639 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 3.9768. Min Range: -3.9768

Max Act: 3.9142. Min Act: -0.1700

Data Index: 1001614 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 3.9768. Min Range: -3.9768

Max Act: 3.8673. Min Act: -0.1700

Data Index: 296489 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 3.9768. Min Range: -3.9768

Max Act: 3.8517. Min Act: -0.1700

Data Index: 78214 (C4 (Web Text))

Max Activating Token Index: 100

Text #6

Max Range: 3.9768. Min Range: -3.9768

Max Act: 3.8517. Min Act: -0.1700

Data Index: 1257262 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 3.9768. Min Range: -3.9768

Max Act: 3.8361. Min Act: -0.1700

Data Index: 58651 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 3.9768. Min Range: -3.9768

Max Act: 3.8048. Min Act: -0.1700

Data Index: 410796 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 3.9768. Min Range: -3.9768

Max Act: 3.8204. Min Act: -0.1700

Data Index: 908417 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 3.9768. Min Range: -3.9768

Max Act: 3.8048. Min Act: -0.1700

Data Index: 459355 (C4 (Web Text))

Max Activating Token Index: 888

Text #11

Max Range: 3.9768. Min Range: -3.9768

Max Act: 3.8048. Min Act: -0.1700

Data Index: 109518 (C4 (Web Text))

Max Activating Token Index: 378

Text #12

Max Range: 3.9768. Min Range: -3.9768

Max Act: 3.7735. Min Act: -0.1700

Data Index: 797831 (C4 (Web Text))

Max Activating Token Index: 388

Text #13

Max Range: 3.9768. Min Range: -3.9768

Max Act: 3.7891. Min Act: -0.1700

Data Index: 1077708 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 3.9768. Min Range: -3.9768

Max Act: 3.7891. Min Act: -0.1700

Data Index: 175170 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 3.9768. Min Range: -3.9768

Max Act: 3.7891. Min Act: -0.1700

Data Index: 928876 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 3.9768. Min Range: -3.9768

Max Act: 3.7578. Min Act: -0.1700

Data Index: 1242262 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 3.9768. Min Range: -3.9768

Max Act: 3.7735. Min Act: -0.1700

Data Index: 1316563 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 3.9768. Min Range: -3.9768

Max Act: 3.7735. Min Act: -0.1700

Data Index: 358242 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 3.9768. Min Range: -3.9768

Max Act: 3.7735. Min Act: -0.1700

Data Index: 936239 (C4 (Web Text))

Max Activating Token Index: 6