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

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

Neuron 1262 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: 10.6138. Min Range: -10.6138

Max Act: 10.6138. Min Act: -0.1700

Data Index: 687034 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 10.6138. Min Range: -10.6138

Max Act: 10.5217. Min Act: -0.1700

Data Index: 764184 (C4 (Web Text))

Max Activating Token Index: 923

Text #2

Max Range: 10.6138. Min Range: -10.6138

Max Act: 10.4886. Min Act: -0.1700

Data Index: 763634 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 10.6138. Min Range: -10.6138

Max Act: 10.4809. Min Act: -0.1700

Data Index: 349439 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 10.6138. Min Range: -10.6138

Max Act: 10.3790. Min Act: -0.1700

Data Index: 1415716 (Python Code)

Max Activating Token Index: 886

Text #5

Max Range: 10.6138. Min Range: -10.6138

Max Act: 10.2929. Min Act: -0.1700

Data Index: 963151 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 10.6138. Min Range: -10.6138

Max Act: 10.2346. Min Act: -0.1700

Data Index: 973711 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 10.6138. Min Range: -10.6138

Max Act: 10.1605. Min Act: -0.1700

Data Index: 411811 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 10.6138. Min Range: -10.6138

Max Act: 10.1262. Min Act: -0.1700

Data Index: 1316251 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 10.6138. Min Range: -10.6138

Max Act: 10.1031. Min Act: -0.1700

Data Index: 485355 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 10.6138. Min Range: -10.6138

Max Act: 10.0930. Min Act: -0.1700

Data Index: 687179 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 10.6138. Min Range: -10.6138

Max Act: 10.0401. Min Act: -0.1700

Data Index: 1391917 (Python Code)

Max Activating Token Index: 661

Text #12

Max Range: 10.6138. Min Range: -10.6138

Max Act: 10.0506. Min Act: -0.1700

Data Index: 894539 (C4 (Web Text))

Max Activating Token Index: 782

Text #13

Max Range: 10.6138. Min Range: -10.6138

Max Act: 10.0450. Min Act: -0.1700

Data Index: 1280167 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 10.6138. Min Range: -10.6138

Max Act: 9.9577. Min Act: -0.1700

Data Index: 1428476 (Python Code)

Max Activating Token Index: 553

Text #15

Max Range: 10.6138. Min Range: -10.6138

Max Act: 9.9077. Min Act: -0.1700

Data Index: 1143050 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 10.6138. Min Range: -10.6138

Max Act: 9.9607. Min Act: -0.1700

Data Index: 587443 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 10.6138. Min Range: -10.6138

Max Act: 9.9045. Min Act: -0.1700

Data Index: 390615 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 10.6138. Min Range: -10.6138

Max Act: 9.9534. Min Act: -0.1700

Data Index: 798195 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 10.6138. Min Range: -10.6138

Max Act: 9.8687. Min Act: -0.1700

Data Index: 723502 (C4 (Web Text))

Max Activating Token Index: 906