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

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

Neuron 1206 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4483. Min Range: -3.4483

Max Act: 3.4483. Min Act: -0.1700

Data Index: 297366 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 3.4483. Min Range: -3.4483

Max Act: 3.4326. Min Act: -0.1700

Data Index: 608770 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 3.4483. Min Range: -3.4483

Max Act: 3.4013. Min Act: -0.1700

Data Index: 479651 (C4 (Web Text))

Max Activating Token Index: 952

Text #3

Max Range: 3.4483. Min Range: -3.4483

Max Act: 3.3856. Min Act: -0.1700

Data Index: 1134436 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 3.4483. Min Range: -3.4483

Max Act: 3.3542. Min Act: -0.1700

Data Index: 514814 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 3.4483. Min Range: -3.4483

Max Act: 3.3699. Min Act: -0.1700

Data Index: 1235079 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 3.4483. Min Range: -3.4483

Max Act: 3.3542. Min Act: -0.1700

Data Index: 532767 (C4 (Web Text))

Max Activating Token Index: 640

Text #7

Max Range: 3.4483. Min Range: -3.4483

Max Act: 3.3699. Min Act: -0.1700

Data Index: 1035472 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 3.4483. Min Range: -3.4483

Max Act: 3.3385. Min Act: -0.1700

Data Index: 183994 (C4 (Web Text))

Max Activating Token Index: 719

Text #9

Max Range: 3.4483. Min Range: -3.4483

Max Act: 3.3385. Min Act: -0.1700

Data Index: 1285119 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 3.4483. Min Range: -3.4483

Max Act: 3.3699. Min Act: -0.1700

Data Index: 188680 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 3.4483. Min Range: -3.4483

Max Act: 3.3699. Min Act: -0.1700

Data Index: 785138 (C4 (Web Text))

Max Activating Token Index: 203

Text #12

Max Range: 3.4483. Min Range: -3.4483

Max Act: 3.3385. Min Act: -0.1700

Data Index: 1139718 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 3.4483. Min Range: -3.4483

Max Act: 3.3385. Min Act: -0.1700

Data Index: 236633 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 3.4483. Min Range: -3.4483

Max Act: 3.3071. Min Act: -0.1700

Data Index: 549524 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 3.4483. Min Range: -3.4483

Max Act: 3.3071. Min Act: -0.1700

Data Index: 914000 (C4 (Web Text))

Max Activating Token Index: 526

Text #16

Max Range: 3.4483. Min Range: -3.4483

Max Act: 3.3228. Min Act: -0.1700

Data Index: 692845 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 3.4483. Min Range: -3.4483

Max Act: 3.3071. Min Act: -0.1700

Data Index: 565420 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 3.4483. Min Range: -3.4483

Max Act: 3.3071. Min Act: -0.1700

Data Index: 1030395 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 3.4483. Min Range: -3.4483

Max Act: 3.2914. Min Act: -0.1700

Data Index: 606036 (C4 (Web Text))

Max Activating Token Index: 535