Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 959 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.9483. Min Range: -3.9483

Max Act: 3.9483. Min Act: -0.1700

Data Index: 1499122 (Python Code)

Max Activating Token Index: 846

Text #1

Max Range: 3.9483. Min Range: -3.9483

Max Act: 3.9170. Min Act: -0.1700

Data Index: 1443690 (Python Code)

Max Activating Token Index: 767

Text #2

Max Range: 3.9483. Min Range: -3.9483

Max Act: 3.9170. Min Act: -0.1700

Data Index: 1382824 (Python Code)

Max Activating Token Index: 769

Text #3

Max Range: 3.9483. Min Range: -3.9483

Max Act: 3.9170. Min Act: -0.1700

Data Index: 1460237 (Python Code)

Max Activating Token Index: 486

Text #4

Max Range: 3.9483. Min Range: -3.9483

Max Act: 3.9483. Min Act: -0.1700

Data Index: 1402911 (Python Code)

Max Activating Token Index: 610

Text #5

Max Range: 3.9483. Min Range: -3.9483

Max Act: 3.9170. Min Act: -0.1700

Data Index: 1381269 (Python Code)

Max Activating Token Index: 913

Text #6

Max Range: 3.9483. Min Range: -3.9483

Max Act: 3.8857. Min Act: -0.1700

Data Index: 1521271 (Python Code)

Max Activating Token Index: 189

Text #7

Max Range: 3.9483. Min Range: -3.9483

Max Act: 3.9170. Min Act: -0.1700

Data Index: 1546980 (Python Code)

Max Activating Token Index: 514

Text #8

Max Range: 3.9483. Min Range: -3.9483

Max Act: 3.8857. Min Act: -0.1700

Data Index: 1370549 (Python Code)

Max Activating Token Index: 867

Text #9

Max Range: 3.9483. Min Range: -3.9483

Max Act: 3.9170. Min Act: -0.1700

Data Index: 1452623 (Python Code)

Max Activating Token Index: 706

Text #10

Max Range: 3.9483. Min Range: -3.9483

Max Act: 3.9170. Min Act: -0.1700

Data Index: 1373410 (Python Code)

Max Activating Token Index: 642

Text #11

Max Range: 3.9483. Min Range: -3.9483

Max Act: 3.9483. Min Act: -0.1700

Data Index: 1507056 (Python Code)

Max Activating Token Index: 612

Text #12

Max Range: 3.9483. Min Range: -3.9483

Max Act: 3.8857. Min Act: -0.1700

Data Index: 1399986 (Python Code)

Max Activating Token Index: 347

Text #13

Max Range: 3.9483. Min Range: -3.9483

Max Act: 3.8545. Min Act: -0.1700

Data Index: 1435251 (Python Code)

Max Activating Token Index: 556

Text #14

Max Range: 3.9483. Min Range: -3.9483

Max Act: 3.8857. Min Act: -0.1700

Data Index: 1400084 (Python Code)

Max Activating Token Index: 792

Text #15

Max Range: 3.9483. Min Range: -3.9483

Max Act: 3.8857. Min Act: -0.1700

Data Index: 1461271 (Python Code)

Max Activating Token Index: 367

Text #16

Max Range: 3.9483. Min Range: -3.9483

Max Act: 3.8545. Min Act: -0.1700

Data Index: 1567670 (Python Code)

Max Activating Token Index: 250

Text #17

Max Range: 3.9483. Min Range: -3.9483

Max Act: 3.9170. Min Act: -0.1700

Data Index: 1588200 (Python Code)

Max Activating Token Index: 626

Text #18

Max Range: 3.9483. Min Range: -3.9483

Max Act: 3.8857. Min Act: -0.1700

Data Index: 1602378 (Python Code)

Max Activating Token Index: 798

Text #19

Max Range: 3.9483. Min Range: -3.9483

Max Act: 3.8857. Min Act: -0.1700

Data Index: 1440553 (Python Code)

Max Activating Token Index: 324