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

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

Neuron 1221 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7450. Min Range: -5.7450

Max Act: 5.7450. Min Act: -0.1700

Data Index: 1161730 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 5.7450. Min Range: -5.7450

Max Act: 5.4950. Min Act: -0.1700

Data Index: 440398 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 5.7450. Min Range: -5.7450

Max Act: 5.5263. Min Act: -0.1700

Data Index: 1104551 (C4 (Web Text))

Max Activating Token Index: 602

Text #3

Max Range: 5.7450. Min Range: -5.7450

Max Act: 5.3700. Min Act: -0.1700

Data Index: 39621 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 5.7450. Min Range: -5.7450

Max Act: 5.3388. Min Act: -0.1700

Data Index: 661453 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 5.7450. Min Range: -5.7450

Max Act: 5.4013. Min Act: -0.1700

Data Index: 171508 (C4 (Web Text))

Max Activating Token Index: 754

Text #6

Max Range: 5.7450. Min Range: -5.7450

Max Act: 5.3700. Min Act: -0.1700

Data Index: 326083 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 5.7450. Min Range: -5.7450

Max Act: 5.2763. Min Act: -0.1700

Data Index: 1239755 (C4 (Web Text))

Max Activating Token Index: 494

Text #8

Max Range: 5.7450. Min Range: -5.7450

Max Act: 5.2763. Min Act: -0.1700

Data Index: 262635 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 5.7450. Min Range: -5.7450

Max Act: 5.2450. Min Act: -0.1700

Data Index: 1334724 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 5.7450. Min Range: -5.7450

Max Act: 5.2450. Min Act: -0.1700

Data Index: 115660 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 5.7450. Min Range: -5.7450

Max Act: 5.2763. Min Act: -0.1700

Data Index: 349300 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 5.7450. Min Range: -5.7450

Max Act: 5.2138. Min Act: -0.1700

Data Index: 266319 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 5.7450. Min Range: -5.7450

Max Act: 5.1825. Min Act: -0.1700

Data Index: 822488 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 5.7450. Min Range: -5.7450

Max Act: 5.2138. Min Act: -0.1700

Data Index: 416537 (C4 (Web Text))

Max Activating Token Index: 298

Text #15

Max Range: 5.7450. Min Range: -5.7450

Max Act: 5.2138. Min Act: -0.1700

Data Index: 814380 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 5.7450. Min Range: -5.7450

Max Act: 5.2450. Min Act: -0.1700

Data Index: 1340781 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 5.7450. Min Range: -5.7450

Max Act: 5.1825. Min Act: -0.1700

Data Index: 735242 (C4 (Web Text))

Max Activating Token Index: 546

Text #18

Max Range: 5.7450. Min Range: -5.7450

Max Act: 5.1513. Min Act: -0.1700

Data Index: 1268738 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 5.7450. Min Range: -5.7450

Max Act: 5.1200. Min Act: -0.1700

Data Index: 92388 (C4 (Web Text))

Max Activating Token Index: 672