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

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

Neuron 800 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: 3.7156. Min Range: -3.7156

Max Act: 3.7156. Min Act: -0.1700

Data Index: 186849 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 3.7156. Min Range: -3.7156

Max Act: 3.5121. Min Act: -0.1700

Data Index: 175730 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 3.7156. Min Range: -3.7156

Max Act: 3.4964. Min Act: -0.1700

Data Index: 746526 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 3.7156. Min Range: -3.7156

Max Act: 3.4651. Min Act: -0.1700

Data Index: 589323 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 3.7156. Min Range: -3.7156

Max Act: 3.4651. Min Act: -0.1700

Data Index: 325119 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 3.7156. Min Range: -3.7156

Max Act: 3.4494. Min Act: -0.1700

Data Index: 519515 (C4 (Web Text))

Max Activating Token Index: 439

Text #6

Max Range: 3.7156. Min Range: -3.7156

Max Act: 3.4181. Min Act: -0.1700

Data Index: 840544 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 3.7156. Min Range: -3.7156

Max Act: 3.4181. Min Act: -0.1700

Data Index: 499023 (C4 (Web Text))

Max Activating Token Index: 526

Text #8

Max Range: 3.7156. Min Range: -3.7156

Max Act: 3.4181. Min Act: -0.1700

Data Index: 1094008 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 3.7156. Min Range: -3.7156

Max Act: 3.4024. Min Act: -0.1700

Data Index: 692054 (C4 (Web Text))

Max Activating Token Index: 736

Text #10

Max Range: 3.7156. Min Range: -3.7156

Max Act: 3.4181. Min Act: -0.1700

Data Index: 1992 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 3.7156. Min Range: -3.7156

Max Act: 3.4337. Min Act: -0.1700

Data Index: 1007979 (C4 (Web Text))

Max Activating Token Index: 582

Text #12

Max Range: 3.7156. Min Range: -3.7156

Max Act: 3.3867. Min Act: -0.1700

Data Index: 798163 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 3.7156. Min Range: -3.7156

Max Act: 3.3867. Min Act: -0.1700

Data Index: 269014 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 3.7156. Min Range: -3.7156

Max Act: 3.3710. Min Act: -0.1700

Data Index: 1184341 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 3.7156. Min Range: -3.7156

Max Act: 3.3710. Min Act: -0.1700

Data Index: 1055693 (C4 (Web Text))

Max Activating Token Index: 1001

Text #16

Max Range: 3.7156. Min Range: -3.7156

Max Act: 3.3710. Min Act: -0.1700

Data Index: 126429 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 3.7156. Min Range: -3.7156

Max Act: 3.3710. Min Act: -0.1700

Data Index: 1231606 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 3.7156. Min Range: -3.7156

Max Act: 3.3553. Min Act: -0.1699

Data Index: 480377 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 3.7156. Min Range: -3.7156

Max Act: 3.3396. Min Act: -0.1700

Data Index: 434727 (C4 (Web Text))

Max Activating Token Index: 509