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

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

Neuron 1129 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: 3.3364. Min Range: -3.3364

Max Act: 3.3364. Min Act: -0.1700

Data Index: 1419730 (Python Code)

Max Activating Token Index: 1011

Text #1

Max Range: 3.3364. Min Range: -3.3364

Max Act: 3.2242. Min Act: -0.1700

Data Index: 357624 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 3.3364. Min Range: -3.3364

Max Act: 3.2186. Min Act: -0.1700

Data Index: 820545 (C4 (Web Text))

Max Activating Token Index: 1018

Text #3

Max Range: 3.3364. Min Range: -3.3364

Max Act: 3.1643. Min Act: -0.1700

Data Index: 247005 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 3.3364. Min Range: -3.3364

Max Act: 3.1244. Min Act: -0.1700

Data Index: 314681 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 3.3364. Min Range: -3.3364

Max Act: 3.1164. Min Act: -0.1700

Data Index: 1212860 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 3.3364. Min Range: -3.3364

Max Act: 3.1123. Min Act: -0.1700

Data Index: 1648534 (Python Code)

Max Activating Token Index: 254

Text #7

Max Range: 3.3364. Min Range: -3.3364

Max Act: 3.0954. Min Act: -0.1700

Data Index: 552673 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 3.3364. Min Range: -3.3364

Max Act: 3.0797. Min Act: -0.1700

Data Index: 1512421 (Python Code)

Max Activating Token Index: 691

Text #9

Max Range: 3.3364. Min Range: -3.3364

Max Act: 3.0963. Min Act: -0.1700

Data Index: 1387837 (Python Code)

Max Activating Token Index: 1022

Text #10

Max Range: 3.3364. Min Range: -3.3364

Max Act: 3.0980. Min Act: -0.1700

Data Index: 1125026 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 3.3364. Min Range: -3.3364

Max Act: 3.0787. Min Act: -0.1700

Data Index: 895076 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 3.3364. Min Range: -3.3364

Max Act: 3.0782. Min Act: -0.1700

Data Index: 1289069 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 3.3364. Min Range: -3.3364

Max Act: 3.0720. Min Act: -0.1700

Data Index: 1405692 (Python Code)

Max Activating Token Index: 424

Text #14

Max Range: 3.3364. Min Range: -3.3364

Max Act: 3.0783. Min Act: -0.1700

Data Index: 1410871 (Python Code)

Max Activating Token Index: 185

Text #15

Max Range: 3.3364. Min Range: -3.3364

Max Act: 3.0634. Min Act: -0.1700

Data Index: 735213 (C4 (Web Text))

Max Activating Token Index: 129

Text #16

Max Range: 3.3364. Min Range: -3.3364

Max Act: 3.0630. Min Act: -0.1700

Data Index: 215583 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 3.3364. Min Range: -3.3364

Max Act: 3.0863. Min Act: -0.1700

Data Index: 342696 (C4 (Web Text))

Max Activating Token Index: 872

Text #18

Max Range: 3.3364. Min Range: -3.3364

Max Act: 3.0570. Min Act: -0.1700

Data Index: 235690 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 3.3364. Min Range: -3.3364

Max Act: 3.0487. Min Act: -0.1700

Data Index: 1395902 (Python Code)

Max Activating Token Index: 749