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

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

Neuron 1250 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: 3.4840. Min Range: -3.4840

Max Act: 3.4840. Min Act: -0.1700

Data Index: 1197730 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 3.4840. Min Range: -3.4840

Max Act: 3.4421. Min Act: -0.1700

Data Index: 628908 (C4 (Web Text))

Max Activating Token Index: 453

Text #2

Max Range: 3.4840. Min Range: -3.4840

Max Act: 3.4208. Min Act: -0.1700

Data Index: 1168178 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 3.4840. Min Range: -3.4840

Max Act: 3.3709. Min Act: -0.1700

Data Index: 697944 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 3.4840. Min Range: -3.4840

Max Act: 3.3177. Min Act: -0.1700

Data Index: 253301 (C4 (Web Text))

Max Activating Token Index: 588

Text #5

Max Range: 3.4840. Min Range: -3.4840

Max Act: 3.2807. Min Act: -0.1700

Data Index: 90678 (C4 (Web Text))

Max Activating Token Index: 530

Text #6

Max Range: 3.4840. Min Range: -3.4840

Max Act: 3.2404. Min Act: -0.1700

Data Index: 1254795 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 3.4840. Min Range: -3.4840

Max Act: 3.2627. Min Act: -0.1700

Data Index: 1207356 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 3.4840. Min Range: -3.4840

Max Act: 3.2518. Min Act: -0.1700

Data Index: 205632 (C4 (Web Text))

Max Activating Token Index: 934

Text #9

Max Range: 3.4840. Min Range: -3.4840

Max Act: 3.2702. Min Act: -0.1700

Data Index: 53735 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 3.4840. Min Range: -3.4840

Max Act: 3.2632. Min Act: -0.1700

Data Index: 265415 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 3.4840. Min Range: -3.4840

Max Act: 3.2177. Min Act: -0.1700

Data Index: 101670 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 3.4840. Min Range: -3.4840

Max Act: 3.2347. Min Act: -0.1700

Data Index: 437846 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 3.4840. Min Range: -3.4840

Max Act: 3.2211. Min Act: -0.1700

Data Index: 41769 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 3.4840. Min Range: -3.4840

Max Act: 3.2156. Min Act: -0.1700

Data Index: 737129 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 3.4840. Min Range: -3.4840

Max Act: 3.2421. Min Act: -0.1700

Data Index: 75876 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 3.4840. Min Range: -3.4840

Max Act: 3.2026. Min Act: -0.1700

Data Index: 960132 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 3.4840. Min Range: -3.4840

Max Act: 3.2211. Min Act: -0.1700

Data Index: 1091804 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 3.4840. Min Range: -3.4840

Max Act: 3.2213. Min Act: -0.1700

Data Index: 305277 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 3.4840. Min Range: -3.4840

Max Act: 3.2166. Min Act: -0.1700

Data Index: 549860 (C4 (Web Text))

Max Activating Token Index: 641