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

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

Neuron 1757 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: 3.4418. Min Range: -3.4418

Max Act: 3.4418. Min Act: -0.1700

Data Index: 769296 (C4 (Web Text))

Max Activating Token Index: 592

Text #1

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.3733. Min Act: -0.1700

Data Index: 103705 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.3550. Min Act: -0.1700

Data Index: 928756 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.3672. Min Act: -0.1700

Data Index: 755565 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.3448. Min Act: -0.1700

Data Index: 454589 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.2930. Min Act: -0.1700

Data Index: 402450 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.2894. Min Act: -0.1700

Data Index: 328337 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.2613. Min Act: -0.1700

Data Index: 573376 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.2450. Min Act: -0.1700

Data Index: 335367 (C4 (Web Text))

Max Activating Token Index: 726

Text #9

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.2415. Min Act: -0.1700

Data Index: 182578 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.2206. Min Act: -0.1700

Data Index: 492543 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.2107. Min Act: -0.1700

Data Index: 209818 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.2074. Min Act: -0.1700

Data Index: 190928 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.1963. Min Act: -0.1700

Data Index: 964619 (C4 (Web Text))

Max Activating Token Index: 363

Text #14

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.2015. Min Act: -0.1700

Data Index: 567921 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.2106. Min Act: -0.1700

Data Index: 598140 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.1569. Min Act: -0.1700

Data Index: 1193422 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.1900. Min Act: -0.1700

Data Index: 295588 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.1616. Min Act: -0.1700

Data Index: 529256 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.1605. Min Act: -0.1700

Data Index: 1102118 (C4 (Web Text))

Max Activating Token Index: 804