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

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

Neuron 86 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: 3.1965. Min Range: -3.1965

Max Act: 3.1965. Min Act: -0.1700

Data Index: 1128575 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 3.1965. Min Range: -3.1965

Max Act: 3.0551. Min Act: -0.1700

Data Index: 1174283 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 3.1965. Min Range: -3.1965

Max Act: 3.0619. Min Act: -0.1699

Data Index: 33800 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 3.1965. Min Range: -3.1965

Max Act: 3.0657. Min Act: -0.1700

Data Index: 1245639 (C4 (Web Text))

Max Activating Token Index: 413

Text #4

Max Range: 3.1965. Min Range: -3.1965

Max Act: 3.0505. Min Act: -0.1700

Data Index: 109292 (C4 (Web Text))

Max Activating Token Index: 365

Text #5

Max Range: 3.1965. Min Range: -3.1965

Max Act: 3.0375. Min Act: -0.1700

Data Index: 234476 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 3.1965. Min Range: -3.1965

Max Act: 3.0222. Min Act: -0.1700

Data Index: 991421 (C4 (Web Text))

Max Activating Token Index: 439

Text #7

Max Range: 3.1965. Min Range: -3.1965

Max Act: 3.0339. Min Act: -0.1700

Data Index: 681641 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 3.1965. Min Range: -3.1965

Max Act: 3.0130. Min Act: -0.1700

Data Index: 97320 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 3.1965. Min Range: -3.1965

Max Act: 3.0204. Min Act: -0.1700

Data Index: 292511 (C4 (Web Text))

Max Activating Token Index: 621

Text #10

Max Range: 3.1965. Min Range: -3.1965

Max Act: 3.0197. Min Act: -0.1700

Data Index: 116183 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 3.1965. Min Range: -3.1965

Max Act: 3.0285. Min Act: -0.1700

Data Index: 430177 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 3.1965. Min Range: -3.1965

Max Act: 3.0147. Min Act: -0.1700

Data Index: 1192789 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 3.1965. Min Range: -3.1965

Max Act: 3.0314. Min Act: -0.1700

Data Index: 500030 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 3.1965. Min Range: -3.1965

Max Act: 3.0055. Min Act: -0.1700

Data Index: 504184 (C4 (Web Text))

Max Activating Token Index: 586

Text #15

Max Range: 3.1965. Min Range: -3.1965

Max Act: 3.0030. Min Act: -0.1700

Data Index: 212195 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 3.1965. Min Range: -3.1965

Max Act: 2.9870. Min Act: -0.1700

Data Index: 306738 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 3.1965. Min Range: -3.1965

Max Act: 3.0110. Min Act: -0.1700

Data Index: 1182522 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 3.1965. Min Range: -3.1965

Max Act: 2.9791. Min Act: -0.1700

Data Index: 1135078 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 3.1965. Min Range: -3.1965

Max Act: 2.9834. Min Act: -0.1700

Data Index: 389921 (C4 (Web Text))

Max Activating Token Index: 844