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

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

Neuron 485 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: 3.2518. Min Range: -3.2518

Max Act: 3.2518. Min Act: -0.1700

Data Index: 847600 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 3.2518. Min Range: -3.2518

Max Act: 3.2203. Min Act: -0.1700

Data Index: 513066 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 3.2518. Min Range: -3.2518

Max Act: 3.1416. Min Act: -0.1700

Data Index: 1333253 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 3.2518. Min Range: -3.2518

Max Act: 3.1259. Min Act: -0.1700

Data Index: 142707 (C4 (Web Text))

Max Activating Token Index: 449

Text #4

Max Range: 3.2518. Min Range: -3.2518

Max Act: 3.1259. Min Act: -0.1700

Data Index: 905733 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 3.2518. Min Range: -3.2518

Max Act: 3.1101. Min Act: -0.1700

Data Index: 476029 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 3.2518. Min Range: -3.2518

Max Act: 3.0470. Min Act: -0.1700

Data Index: 1068322 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 3.2518. Min Range: -3.2518

Max Act: 3.0628. Min Act: -0.1700

Data Index: 1056041 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 3.2518. Min Range: -3.2518

Max Act: 3.0628. Min Act: -0.1700

Data Index: 1339033 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 3.2518. Min Range: -3.2518

Max Act: 3.0312. Min Act: -0.1700

Data Index: 66764 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 3.2518. Min Range: -3.2518

Max Act: 3.0154. Min Act: -0.1700

Data Index: 271260 (C4 (Web Text))

Max Activating Token Index: 212

Text #11

Max Range: 3.2518. Min Range: -3.2518

Max Act: 3.0312. Min Act: -0.1700

Data Index: 103441 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 3.2518. Min Range: -3.2518

Max Act: 3.0470. Min Act: -0.1700

Data Index: 789669 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 3.2518. Min Range: -3.2518

Max Act: 2.9996. Min Act: -0.1700

Data Index: 734921 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 3.2518. Min Range: -3.2518

Max Act: 2.9996. Min Act: -0.1700

Data Index: 898969 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 3.2518. Min Range: -3.2518

Max Act: 3.0154. Min Act: -0.1700

Data Index: 878390 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 3.2518. Min Range: -3.2518

Max Act: 2.9996. Min Act: -0.1700

Data Index: 575429 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 3.2518. Min Range: -3.2518

Max Act: 2.9996. Min Act: -0.1700

Data Index: 402517 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 3.2518. Min Range: -3.2518

Max Act: 2.9996. Min Act: -0.1700

Data Index: 188285 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 3.2518. Min Range: -3.2518

Max Act: 2.9996. Min Act: -0.1700

Data Index: 602611 (C4 (Web Text))

Max Activating Token Index: 34