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

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

Neuron 1577 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: 3.2478. Min Range: -3.2478

Max Act: 3.2478. Min Act: -0.1700

Data Index: 232681 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 3.2478. Min Range: -3.2478

Max Act: 3.1849. Min Act: -0.1700

Data Index: 1015917 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 3.2478. Min Range: -3.2478

Max Act: 3.1691. Min Act: -0.1700

Data Index: 1039276 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 3.2478. Min Range: -3.2478

Max Act: 3.1377. Min Act: -0.1700

Data Index: 270695 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 3.2478. Min Range: -3.2478

Max Act: 3.1219. Min Act: -0.1700

Data Index: 785389 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 3.2478. Min Range: -3.2478

Max Act: 3.1219. Min Act: -0.1700

Data Index: 367453 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 3.2478. Min Range: -3.2478

Max Act: 3.1219. Min Act: -0.1700

Data Index: 1263350 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 3.2478. Min Range: -3.2478

Max Act: 3.1061. Min Act: -0.1700

Data Index: 310355 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 3.2478. Min Range: -3.2478

Max Act: 3.1377. Min Act: -0.1700

Data Index: 1063906 (C4 (Web Text))

Max Activating Token Index: 422

Text #9

Max Range: 3.2478. Min Range: -3.2478

Max Act: 3.1219. Min Act: -0.1700

Data Index: 216842 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 3.2478. Min Range: -3.2478

Max Act: 3.1061. Min Act: -0.1700

Data Index: 332731 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 3.2478. Min Range: -3.2478

Max Act: 3.1061. Min Act: -0.1700

Data Index: 917435 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 3.2478. Min Range: -3.2478

Max Act: 3.1061. Min Act: -0.1700

Data Index: 1312146 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 3.2478. Min Range: -3.2478

Max Act: 3.1061. Min Act: -0.1700

Data Index: 81433 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 3.2478. Min Range: -3.2478

Max Act: 3.1061. Min Act: -0.1700

Data Index: 29196 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 3.2478. Min Range: -3.2478

Max Act: 3.1061. Min Act: -0.1700

Data Index: 202597 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 3.2478. Min Range: -3.2478

Max Act: 3.0904. Min Act: -0.1700

Data Index: 299528 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 3.2478. Min Range: -3.2478

Max Act: 3.1061. Min Act: -0.1700

Data Index: 244918 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 3.2478. Min Range: -3.2478

Max Act: 3.0904. Min Act: -0.1700

Data Index: 207074 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 3.2478. Min Range: -3.2478

Max Act: 3.0746. Min Act: -0.1700

Data Index: 305056 (C4 (Web Text))

Max Activating Token Index: 121