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

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

Neuron 500 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: 3.9381. Min Range: -3.9381

Max Act: 3.9381. Min Act: -0.1700

Data Index: 1386051 (Python Code)

Max Activating Token Index: 867

Text #1

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.7471. Min Act: -0.1684

Data Index: 1459918 (Python Code)

Max Activating Token Index: 510

Text #2

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.6757. Min Act: -0.1700

Data Index: 1559763 (Python Code)

Max Activating Token Index: 66

Text #3

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.6510. Min Act: -0.1700

Data Index: 983772 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.6407. Min Act: -0.1687

Data Index: 1305365 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.6259. Min Act: -0.1700

Data Index: 1408892 (Python Code)

Max Activating Token Index: 177

Text #6

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.6352. Min Act: -0.1698

Data Index: 759454 (C4 (Web Text))

Max Activating Token Index: 872

Text #7

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.6122. Min Act: -0.1700

Data Index: 1585647 (Python Code)

Max Activating Token Index: 672

Text #8

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.6210. Min Act: -0.1700

Data Index: 1501491 (Python Code)

Max Activating Token Index: 937

Text #9

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.5961. Min Act: -0.1700

Data Index: 756407 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.6039. Min Act: -0.1700

Data Index: 1480529 (Python Code)

Max Activating Token Index: 315

Text #11

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.5784. Min Act: -0.1700

Data Index: 1491226 (Python Code)

Max Activating Token Index: 951

Text #12

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.5557. Min Act: -0.1700

Data Index: 1412934 (Python Code)

Max Activating Token Index: 1013

Text #13

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.5290. Min Act: -0.1700

Data Index: 1629970 (Python Code)

Max Activating Token Index: 324

Text #14

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.5061. Min Act: -0.1700

Data Index: 1611724 (Python Code)

Max Activating Token Index: 916

Text #15

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.5079. Min Act: -0.1700

Data Index: 1521969 (Python Code)

Max Activating Token Index: 973

Text #16

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.5058. Min Act: -0.1700

Data Index: 1556114 (Python Code)

Max Activating Token Index: 693

Text #17

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.5122. Min Act: -0.1700

Data Index: 1467093 (Python Code)

Max Activating Token Index: 954

Text #18

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.5081. Min Act: -0.1700

Data Index: 1451695 (Python Code)

Max Activating Token Index: 200

Text #19

Max Range: 3.9381. Min Range: -3.9381

Max Act: 3.4955. Min Act: -0.1699

Data Index: 1650476 (Python Code)

Max Activating Token Index: 438