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

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

Neuron 142 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.2208. Min Range: -3.2208

Max Act: 3.2208. Min Act: -0.1700

Data Index: 453685 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 3.2208. Min Range: -3.2208

Max Act: 3.1893. Min Act: -0.1700

Data Index: 712183 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 3.2208. Min Range: -3.2208

Max Act: 3.2050. Min Act: -0.1700

Data Index: 464117 (C4 (Web Text))

Max Activating Token Index: 213

Text #3

Max Range: 3.2208. Min Range: -3.2208

Max Act: 3.1736. Min Act: -0.1700

Data Index: 46147 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 3.2208. Min Range: -3.2208

Max Act: 3.1893. Min Act: -0.1700

Data Index: 772888 (C4 (Web Text))

Max Activating Token Index: 389

Text #5

Max Range: 3.2208. Min Range: -3.2208

Max Act: 3.1736. Min Act: -0.1700

Data Index: 962618 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 3.2208. Min Range: -3.2208

Max Act: 3.1893. Min Act: -0.1700

Data Index: 1195940 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 3.2208. Min Range: -3.2208

Max Act: 3.1736. Min Act: -0.1700

Data Index: 26480 (C4 (Web Text))

Max Activating Token Index: 544

Text #8

Max Range: 3.2208. Min Range: -3.2208

Max Act: 3.1421. Min Act: -0.1700

Data Index: 846070 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 3.2208. Min Range: -3.2208

Max Act: 3.1893. Min Act: -0.1700

Data Index: 770563 (C4 (Web Text))

Max Activating Token Index: 851

Text #10

Max Range: 3.2208. Min Range: -3.2208

Max Act: 3.1578. Min Act: -0.1700

Data Index: 730315 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 3.2208. Min Range: -3.2208

Max Act: 3.1736. Min Act: -0.1700

Data Index: 548875 (C4 (Web Text))

Max Activating Token Index: 320

Text #12

Max Range: 3.2208. Min Range: -3.2208

Max Act: 3.1578. Min Act: -0.1700

Data Index: 999109 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 3.2208. Min Range: -3.2208

Max Act: 3.1578. Min Act: -0.1700

Data Index: 575830 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 3.2208. Min Range: -3.2208

Max Act: 3.1263. Min Act: -0.1700

Data Index: 880763 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 3.2208. Min Range: -3.2208

Max Act: 3.1893. Min Act: -0.1700

Data Index: 326255 (C4 (Web Text))

Max Activating Token Index: 916

Text #16

Max Range: 3.2208. Min Range: -3.2208

Max Act: 3.1578. Min Act: -0.1700

Data Index: 1098803 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 3.2208. Min Range: -3.2208

Max Act: 3.1578. Min Act: -0.1700

Data Index: 838278 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 3.2208. Min Range: -3.2208

Max Act: 3.1421. Min Act: -0.1700

Data Index: 897021 (C4 (Web Text))

Max Activating Token Index: 877

Text #19

Max Range: 3.2208. Min Range: -3.2208

Max Act: 3.1736. Min Act: -0.1700

Data Index: 103667 (C4 (Web Text))

Max Activating Token Index: 898