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

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

Neuron 1184 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: 4.3451. Min Range: -4.3451

Max Act: 4.3451. Min Act: -0.1700

Data Index: 1339036 (C4 (Web Text))

Max Activating Token Index: 513

Text #1

Max Range: 4.3451. Min Range: -4.3451

Max Act: 4.1232. Min Act: -0.1700

Data Index: 126646 (C4 (Web Text))

Max Activating Token Index: 286

Text #2

Max Range: 4.3451. Min Range: -4.3451

Max Act: 4.0623. Min Act: -0.1700

Data Index: 643926 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 4.3451. Min Range: -4.3451

Max Act: 4.0512. Min Act: -0.1700

Data Index: 1214682 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 4.3451. Min Range: -4.3451

Max Act: 4.0363. Min Act: -0.1700

Data Index: 252362 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 4.3451. Min Range: -4.3451

Max Act: 4.0850. Min Act: -0.1700

Data Index: 700963 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 4.3451. Min Range: -4.3451

Max Act: 4.0762. Min Act: -0.1700

Data Index: 484696 (C4 (Web Text))

Max Activating Token Index: 485

Text #7

Max Range: 4.3451. Min Range: -4.3451

Max Act: 4.0158. Min Act: -0.1700

Data Index: 866508 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 4.3451. Min Range: -4.3451

Max Act: 4.0040. Min Act: -0.1700

Data Index: 954080 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 4.3451. Min Range: -4.3451

Max Act: 4.0052. Min Act: -0.1700

Data Index: 992875 (C4 (Web Text))

Max Activating Token Index: 348

Text #10

Max Range: 4.3451. Min Range: -4.3451

Max Act: 3.9766. Min Act: -0.1700

Data Index: 935849 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 4.3451. Min Range: -4.3451

Max Act: 3.9432. Min Act: -0.1700

Data Index: 742795 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 4.3451. Min Range: -4.3451

Max Act: 3.9435. Min Act: -0.1700

Data Index: 658087 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 4.3451. Min Range: -4.3451

Max Act: 3.8992. Min Act: -0.1700

Data Index: 862177 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 4.3451. Min Range: -4.3451

Max Act: 3.9007. Min Act: -0.1700

Data Index: 882893 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 4.3451. Min Range: -4.3451

Max Act: 3.9100. Min Act: -0.1700

Data Index: 977623 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 4.3451. Min Range: -4.3451

Max Act: 3.9065. Min Act: -0.1700

Data Index: 739474 (C4 (Web Text))

Max Activating Token Index: 284

Text #17

Max Range: 4.3451. Min Range: -4.3451

Max Act: 3.8671. Min Act: -0.1700

Data Index: 1365670 (Python Code)

Max Activating Token Index: 291

Text #18

Max Range: 4.3451. Min Range: -4.3451

Max Act: 3.8766. Min Act: -0.1700

Data Index: 1368243 (Python Code)

Max Activating Token Index: 975

Text #19

Max Range: 4.3451. Min Range: -4.3451

Max Act: 3.8821. Min Act: -0.1700

Data Index: 1568467 (Python Code)

Max Activating Token Index: 983