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

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

Neuron 719 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: 3.2957. Min Range: -3.2957

Max Act: 3.2957. Min Act: -0.1700

Data Index: 665069 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 3.2957. Min Range: -3.2957

Max Act: 3.2802. Min Act: -0.1700

Data Index: 294921 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 3.2957. Min Range: -3.2957

Max Act: 3.2657. Min Act: -0.1700

Data Index: 801598 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 3.2957. Min Range: -3.2957

Max Act: 3.2566. Min Act: -0.1700

Data Index: 461301 (C4 (Web Text))

Max Activating Token Index: 705

Text #4

Max Range: 3.2957. Min Range: -3.2957

Max Act: 3.2430. Min Act: -0.1700

Data Index: 1108948 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 3.2957. Min Range: -3.2957

Max Act: 3.1964. Min Act: -0.1700

Data Index: 748885 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 3.2957. Min Range: -3.2957

Max Act: 3.1873. Min Act: -0.1700

Data Index: 1244434 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 3.2957. Min Range: -3.2957

Max Act: 3.1913. Min Act: -0.1700

Data Index: 328014 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 3.2957. Min Range: -3.2957

Max Act: 3.1816. Min Act: -0.1700

Data Index: 124699 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 3.2957. Min Range: -3.2957

Max Act: 3.1591. Min Act: -0.1700

Data Index: 771610 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 3.2957. Min Range: -3.2957

Max Act: 3.1581. Min Act: -0.1700

Data Index: 1248461 (C4 (Web Text))

Max Activating Token Index: 88

Text #11

Max Range: 3.2957. Min Range: -3.2957

Max Act: 3.1687. Min Act: -0.1700

Data Index: 1095047 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 3.2957. Min Range: -3.2957

Max Act: 3.1589. Min Act: -0.1700

Data Index: 18948 (C4 (Web Text))

Max Activating Token Index: 711

Text #13

Max Range: 3.2957. Min Range: -3.2957

Max Act: 3.1465. Min Act: -0.1700

Data Index: 1079780 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 3.2957. Min Range: -3.2957

Max Act: 3.1488. Min Act: -0.1700

Data Index: 1187834 (C4 (Web Text))

Max Activating Token Index: 675

Text #15

Max Range: 3.2957. Min Range: -3.2957

Max Act: 3.1387. Min Act: -0.1700

Data Index: 927568 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 3.2957. Min Range: -3.2957

Max Act: 3.1262. Min Act: -0.1700

Data Index: 894675 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 3.2957. Min Range: -3.2957

Max Act: 3.1421. Min Act: -0.1700

Data Index: 44176 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 3.2957. Min Range: -3.2957

Max Act: 3.1232. Min Act: -0.1700

Data Index: 448546 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 3.2957. Min Range: -3.2957

Max Act: 3.1295. Min Act: -0.1700

Data Index: 1188815 (C4 (Web Text))

Max Activating Token Index: 377