Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1857 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.3199. Min Range: -3.3199

Max Act: 3.3199. Min Act: -0.1700

Data Index: 214398 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 3.3199. Min Range: -3.3199

Max Act: 3.2413. Min Act: -0.1700

Data Index: 12080 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 3.3199. Min Range: -3.3199

Max Act: 3.2323. Min Act: -0.1700

Data Index: 611916 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 3.3199. Min Range: -3.3199

Max Act: 3.2257. Min Act: -0.1700

Data Index: 1350048 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 3.3199. Min Range: -3.3199

Max Act: 3.1717. Min Act: -0.1700

Data Index: 589175 (C4 (Web Text))

Max Activating Token Index: 312

Text #5

Max Range: 3.3199. Min Range: -3.3199

Max Act: 3.1587. Min Act: -0.1700

Data Index: 1107703 (C4 (Web Text))

Max Activating Token Index: 220

Text #6

Max Range: 3.3199. Min Range: -3.3199

Max Act: 3.1394. Min Act: -0.1700

Data Index: 275961 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 3.3199. Min Range: -3.3199

Max Act: 3.1364. Min Act: -0.1700

Data Index: 1292845 (C4 (Web Text))

Max Activating Token Index: 823

Text #8

Max Range: 3.3199. Min Range: -3.3199

Max Act: 3.1253. Min Act: -0.1700

Data Index: 621732 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 3.3199. Min Range: -3.3199

Max Act: 3.0826. Min Act: -0.1700

Data Index: 119620 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 3.3199. Min Range: -3.3199

Max Act: 3.0833. Min Act: -0.1700

Data Index: 1104911 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 3.3199. Min Range: -3.3199

Max Act: 3.0835. Min Act: -0.1700

Data Index: 337198 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 3.3199. Min Range: -3.3199

Max Act: 3.0763. Min Act: -0.1700

Data Index: 406583 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 3.3199. Min Range: -3.3199

Max Act: 3.0792. Min Act: -0.1700

Data Index: 1148933 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 3.3199. Min Range: -3.3199

Max Act: 3.0603. Min Act: -0.1700

Data Index: 1011883 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 3.3199. Min Range: -3.3199

Max Act: 3.0555. Min Act: -0.1700

Data Index: 8207 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 3.3199. Min Range: -3.3199

Max Act: 3.0632. Min Act: -0.1700

Data Index: 518957 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 3.3199. Min Range: -3.3199

Max Act: 3.0605. Min Act: -0.1700

Data Index: 1093203 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 3.3199. Min Range: -3.3199

Max Act: 3.0596. Min Act: -0.1700

Data Index: 482877 (C4 (Web Text))

Max Activating Token Index: 93

Text #19

Max Range: 3.3199. Min Range: -3.3199

Max Act: 3.0591. Min Act: -0.1700

Data Index: 92004 (C4 (Web Text))

Max Activating Token Index: 444