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

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

Neuron 1248 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: 3.9261. Min Range: -3.9261

Max Act: 3.9261. Min Act: -0.1700

Data Index: 543615 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.8891. Min Act: -0.1700

Data Index: 1081184 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.8253. Min Act: -0.1700

Data Index: 1068127 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.7954. Min Act: -0.1700

Data Index: 381779 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.7432. Min Act: -0.1700

Data Index: 929081 (C4 (Web Text))

Max Activating Token Index: 630

Text #5

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.7163. Min Act: -0.1700

Data Index: 959713 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.7185. Min Act: -0.1683

Data Index: 137327 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.6948. Min Act: -0.1700

Data Index: 165458 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.7022. Min Act: -0.1700

Data Index: 262630 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.6992. Min Act: -0.1700

Data Index: 1080516 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.6955. Min Act: -0.1700

Data Index: 725190 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.6838. Min Act: -0.1700

Data Index: 406462 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.6742. Min Act: -0.1700

Data Index: 1313846 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.6523. Min Act: -0.1687

Data Index: 888672 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.6458. Min Act: -0.1700

Data Index: 641684 (C4 (Web Text))

Max Activating Token Index: 716

Text #15

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.6257. Min Act: -0.1700

Data Index: 326313 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.6464. Min Act: -0.1700

Data Index: 107204 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.6413. Min Act: -0.1700

Data Index: 963415 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.6545. Min Act: -0.1694

Data Index: 229269 (C4 (Web Text))

Max Activating Token Index: 986

Text #19

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.6285. Min Act: -0.1700

Data Index: 208111 (C4 (Web Text))

Max Activating Token Index: 753