Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 922 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.2347. Min Range: -3.2347

Max Act: 3.2347. Min Act: -0.1700

Data Index: 1629869 (Python Code)

Max Activating Token Index: 462

Text #1

Max Range: 3.2347. Min Range: -3.2347

Max Act: 3.1875. Min Act: -0.1700

Data Index: 1557718 (Python Code)

Max Activating Token Index: 84

Text #2

Max Range: 3.2347. Min Range: -3.2347

Max Act: 3.1717. Min Act: -0.1700

Data Index: 1632160 (Python Code)

Max Activating Token Index: 6

Text #3

Max Range: 3.2347. Min Range: -3.2347

Max Act: 3.1717. Min Act: -0.1700

Data Index: 1542464 (Python Code)

Max Activating Token Index: 960

Text #4

Max Range: 3.2347. Min Range: -3.2347

Max Act: 3.1875. Min Act: -0.1700

Data Index: 1579958 (Python Code)

Max Activating Token Index: 582

Text #5

Max Range: 3.2347. Min Range: -3.2347

Max Act: 3.1875. Min Act: -0.1700

Data Index: 1656336 (Python Code)

Max Activating Token Index: 406

Text #6

Max Range: 3.2347. Min Range: -3.2347

Max Act: 3.1717. Min Act: -0.1700

Data Index: 1543469 (Python Code)

Max Activating Token Index: 153

Text #7

Max Range: 3.2347. Min Range: -3.2347

Max Act: 3.1717. Min Act: -0.1700

Data Index: 1463107 (Python Code)

Max Activating Token Index: 285

Text #8

Max Range: 3.2347. Min Range: -3.2347

Max Act: 3.1560. Min Act: -0.1700

Data Index: 1501280 (Python Code)

Max Activating Token Index: 684

Text #9

Max Range: 3.2347. Min Range: -3.2347

Max Act: 3.1717. Min Act: -0.1700

Data Index: 1558690 (Python Code)

Max Activating Token Index: 635

Text #10

Max Range: 3.2347. Min Range: -3.2347

Max Act: 3.1245. Min Act: -0.1700

Data Index: 1534369 (Python Code)

Max Activating Token Index: 497

Text #11

Max Range: 3.2347. Min Range: -3.2347

Max Act: 3.1402. Min Act: -0.1700

Data Index: 1556619 (Python Code)

Max Activating Token Index: 278

Text #12

Max Range: 3.2347. Min Range: -3.2347

Max Act: 3.1717. Min Act: -0.1700

Data Index: 1514306 (Python Code)

Max Activating Token Index: 651

Text #13

Max Range: 3.2347. Min Range: -3.2347

Max Act: 3.1402. Min Act: -0.1700

Data Index: 1548002 (Python Code)

Max Activating Token Index: 702

Text #14

Max Range: 3.2347. Min Range: -3.2347

Max Act: 3.1560. Min Act: -0.1700

Data Index: 1361368 (Python Code)

Max Activating Token Index: 396

Text #15

Max Range: 3.2347. Min Range: -3.2347

Max Act: 3.1402. Min Act: -0.1700

Data Index: 1562332 (Python Code)

Max Activating Token Index: 782

Text #16

Max Range: 3.2347. Min Range: -3.2347

Max Act: 3.1402. Min Act: -0.1700

Data Index: 1401459 (Python Code)

Max Activating Token Index: 21

Text #17

Max Range: 3.2347. Min Range: -3.2347

Max Act: 3.1402. Min Act: -0.1700

Data Index: 1510623 (Python Code)

Max Activating Token Index: 153

Text #18

Max Range: 3.2347. Min Range: -3.2347

Max Act: 3.1402. Min Act: -0.1700

Data Index: 1438705 (Python Code)

Max Activating Token Index: 748

Text #19

Max Range: 3.2347. Min Range: -3.2347

Max Act: 3.1402. Min Act: -0.1700

Data Index: 1635156 (Python Code)

Max Activating Token Index: 643