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

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

Neuron 65 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: 3.2331. Min Range: -3.2331

Max Act: 3.2331. Min Act: -0.1700

Data Index: 149016 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 3.2331. Min Range: -3.2331

Max Act: 3.1156. Min Act: -0.1700

Data Index: 1622035 (Python Code)

Max Activating Token Index: 943

Text #2

Max Range: 3.2331. Min Range: -3.2331

Max Act: 3.1112. Min Act: -0.1700

Data Index: 959534 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 3.2331. Min Range: -3.2331

Max Act: 3.0421. Min Act: -0.1700

Data Index: 695115 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 3.2331. Min Range: -3.2331

Max Act: 3.0533. Min Act: -0.1700

Data Index: 383985 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 3.2331. Min Range: -3.2331

Max Act: 3.0276. Min Act: -0.1700

Data Index: 207741 (C4 (Web Text))

Max Activating Token Index: 100

Text #6

Max Range: 3.2331. Min Range: -3.2331

Max Act: 3.0334. Min Act: -0.1700

Data Index: 1367386 (Python Code)

Max Activating Token Index: 404

Text #7

Max Range: 3.2331. Min Range: -3.2331

Max Act: 3.0344. Min Act: -0.1700

Data Index: 616435 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 3.2331. Min Range: -3.2331

Max Act: 3.0529. Min Act: -0.1700

Data Index: 797242 (C4 (Web Text))

Max Activating Token Index: 666

Text #9

Max Range: 3.2331. Min Range: -3.2331

Max Act: 2.9954. Min Act: -0.1700

Data Index: 1328383 (C4 (Web Text))

Max Activating Token Index: 746

Text #10

Max Range: 3.2331. Min Range: -3.2331

Max Act: 3.0161. Min Act: -0.1700

Data Index: 1481608 (Python Code)

Max Activating Token Index: 709

Text #11

Max Range: 3.2331. Min Range: -3.2331

Max Act: 3.0327. Min Act: -0.1700

Data Index: 1419600 (Python Code)

Max Activating Token Index: 682

Text #12

Max Range: 3.2331. Min Range: -3.2331

Max Act: 3.0086. Min Act: -0.1700

Data Index: 764367 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 3.2331. Min Range: -3.2331

Max Act: 2.9922. Min Act: -0.1700

Data Index: 754207 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 3.2331. Min Range: -3.2331

Max Act: 2.9838. Min Act: -0.1700

Data Index: 1081416 (C4 (Web Text))

Max Activating Token Index: 951

Text #15

Max Range: 3.2331. Min Range: -3.2331

Max Act: 2.9717. Min Act: -0.1700

Data Index: 546015 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 3.2331. Min Range: -3.2331

Max Act: 2.9703. Min Act: -0.1700

Data Index: 1006339 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 3.2331. Min Range: -3.2331

Max Act: 2.9883. Min Act: -0.1700

Data Index: 1547587 (Python Code)

Max Activating Token Index: 358

Text #18

Max Range: 3.2331. Min Range: -3.2331

Max Act: 2.9589. Min Act: -0.1700

Data Index: 220293 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 3.2331. Min Range: -3.2331

Max Act: 2.9663. Min Act: -0.1700

Data Index: 1227324 (C4 (Web Text))

Max Activating Token Index: 376