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

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

Neuron 1050 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: 2.9870. Min Range: -2.9870

Max Act: 2.9870. Min Act: -0.1700

Data Index: 797696 (C4 (Web Text))

Max Activating Token Index: 431

Text #1

Max Range: 2.9870. Min Range: -2.9870

Max Act: 2.8632. Min Act: -0.1700

Data Index: 1425035 (Python Code)

Max Activating Token Index: 812

Text #2

Max Range: 2.9870. Min Range: -2.9870

Max Act: 2.8303. Min Act: -0.1700

Data Index: 1091376 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 2.9870. Min Range: -2.9870

Max Act: 2.7324. Min Act: -0.1700

Data Index: 815188 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 2.9870. Min Range: -2.9870

Max Act: 2.7536. Min Act: -0.1700

Data Index: 111394 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 2.9870. Min Range: -2.9870

Max Act: 2.7286. Min Act: -0.1700

Data Index: 1413543 (Python Code)

Max Activating Token Index: 362

Text #6

Max Range: 2.9870. Min Range: -2.9870

Max Act: 2.7128. Min Act: -0.1700

Data Index: 581872 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 2.9870. Min Range: -2.9870

Max Act: 2.6996. Min Act: -0.1700

Data Index: 127058 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 2.9870. Min Range: -2.9870

Max Act: 2.6901. Min Act: -0.1700

Data Index: 1366980 (Python Code)

Max Activating Token Index: 75

Text #9

Max Range: 2.9870. Min Range: -2.9870

Max Act: 2.6856. Min Act: -0.1700

Data Index: 1523636 (Python Code)

Max Activating Token Index: 285

Text #10

Max Range: 2.9870. Min Range: -2.9870

Max Act: 2.6909. Min Act: -0.1700

Data Index: 896592 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 2.9870. Min Range: -2.9870

Max Act: 2.6925. Min Act: -0.1700

Data Index: 701767 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 2.9870. Min Range: -2.9870

Max Act: 2.6985. Min Act: -0.1700

Data Index: 43276 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 2.9870. Min Range: -2.9870

Max Act: 2.6682. Min Act: -0.1700

Data Index: 856065 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 2.9870. Min Range: -2.9870

Max Act: 2.6800. Min Act: -0.1700

Data Index: 1050544 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 2.9870. Min Range: -2.9870

Max Act: 2.6624. Min Act: -0.1700

Data Index: 182216 (C4 (Web Text))

Max Activating Token Index: 542

Text #16

Max Range: 2.9870. Min Range: -2.9870

Max Act: 2.6712. Min Act: -0.1700

Data Index: 1251060 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 2.9870. Min Range: -2.9870

Max Act: 2.6575. Min Act: -0.1700

Data Index: 1084115 (C4 (Web Text))

Max Activating Token Index: 556

Text #18

Max Range: 2.9870. Min Range: -2.9870

Max Act: 2.6678. Min Act: -0.1700

Data Index: 293833 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 2.9870. Min Range: -2.9870

Max Act: 2.6716. Min Act: -0.1700

Data Index: 794989 (C4 (Web Text))

Max Activating Token Index: 734