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

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

Neuron 1583 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: 3.2070. Min Range: -3.2070

Max Act: 3.2070. Min Act: -0.1700

Data Index: 1644904 (Python Code)

Max Activating Token Index: 116

Text #1

Max Range: 3.2070. Min Range: -3.2070

Max Act: 3.1823. Min Act: -0.1700

Data Index: 1643648 (Python Code)

Max Activating Token Index: 598

Text #2

Max Range: 3.2070. Min Range: -3.2070

Max Act: 3.1282. Min Act: -0.1700

Data Index: 1184210 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 3.2070. Min Range: -3.2070

Max Act: 3.1297. Min Act: -0.1699

Data Index: 1396407 (Python Code)

Max Activating Token Index: 886

Text #4

Max Range: 3.2070. Min Range: -3.2070

Max Act: 3.1370. Min Act: -0.1700

Data Index: 1431428 (Python Code)

Max Activating Token Index: 251

Text #5

Max Range: 3.2070. Min Range: -3.2070

Max Act: 3.1036. Min Act: -0.1699

Data Index: 633208 (C4 (Web Text))

Max Activating Token Index: 412

Text #6

Max Range: 3.2070. Min Range: -3.2070

Max Act: 3.0976. Min Act: -0.1700

Data Index: 1631806 (Python Code)

Max Activating Token Index: 155

Text #7

Max Range: 3.2070. Min Range: -3.2070

Max Act: 3.0633. Min Act: -0.1700

Data Index: 781087 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 3.2070. Min Range: -3.2070

Max Act: 3.0653. Min Act: -0.1700

Data Index: 827688 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 3.2070. Min Range: -3.2070

Max Act: 3.0430. Min Act: -0.1700

Data Index: 390574 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 3.2070. Min Range: -3.2070

Max Act: 3.0124. Min Act: -0.1697

Data Index: 1628486 (Python Code)

Max Activating Token Index: 730

Text #11

Max Range: 3.2070. Min Range: -3.2070

Max Act: 3.0063. Min Act: -0.1699

Data Index: 729904 (C4 (Web Text))

Max Activating Token Index: 805

Text #12

Max Range: 3.2070. Min Range: -3.2070

Max Act: 2.9979. Min Act: -0.1700

Data Index: 308247 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 3.2070. Min Range: -3.2070

Max Act: 2.9946. Min Act: -0.1700

Data Index: 841409 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 3.2070. Min Range: -3.2070

Max Act: 2.9805. Min Act: -0.1700

Data Index: 1642329 (Python Code)

Max Activating Token Index: 746

Text #15

Max Range: 3.2070. Min Range: -3.2070

Max Act: 2.9791. Min Act: -0.1700

Data Index: 1594511 (Python Code)

Max Activating Token Index: 993

Text #16

Max Range: 3.2070. Min Range: -3.2070

Max Act: 2.9662. Min Act: -0.1700

Data Index: 1390522 (Python Code)

Max Activating Token Index: 56

Text #17

Max Range: 3.2070. Min Range: -3.2070

Max Act: 2.9669. Min Act: -0.1700

Data Index: 1611063 (Python Code)

Max Activating Token Index: 771

Text #18

Max Range: 3.2070. Min Range: -3.2070

Max Act: 2.9734. Min Act: -0.1700

Data Index: 1566483 (Python Code)

Max Activating Token Index: 640

Text #19

Max Range: 3.2070. Min Range: -3.2070

Max Act: 2.9639. Min Act: -0.1700

Data Index: 1632617 (Python Code)

Max Activating Token Index: 255