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

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

Neuron 1828 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: 4.0432. Min Range: -4.0432

Max Act: 4.0432. Min Act: -0.1700

Data Index: 732188 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 4.0432. Min Range: -4.0432

Max Act: 4.0255. Min Act: -0.1700

Data Index: 817594 (C4 (Web Text))

Max Activating Token Index: 303

Text #2

Max Range: 4.0432. Min Range: -4.0432

Max Act: 4.0056. Min Act: -0.1700

Data Index: 10402 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 4.0432. Min Range: -4.0432

Max Act: 3.9961. Min Act: -0.1700

Data Index: 1035596 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 4.0432. Min Range: -4.0432

Max Act: 3.9589. Min Act: -0.1700

Data Index: 1143183 (C4 (Web Text))

Max Activating Token Index: 955

Text #5

Max Range: 4.0432. Min Range: -4.0432

Max Act: 3.9476. Min Act: -0.1700

Data Index: 1197337 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 4.0432. Min Range: -4.0432

Max Act: 3.9505. Min Act: -0.1700

Data Index: 126145 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 4.0432. Min Range: -4.0432

Max Act: 3.9154. Min Act: -0.1700

Data Index: 159271 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 4.0432. Min Range: -4.0432

Max Act: 3.9341. Min Act: -0.1700

Data Index: 123600 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 4.0432. Min Range: -4.0432

Max Act: 3.9527. Min Act: -0.1700

Data Index: 956767 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 4.0432. Min Range: -4.0432

Max Act: 3.9190. Min Act: -0.1700

Data Index: 442675 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 4.0432. Min Range: -4.0432

Max Act: 3.9150. Min Act: -0.1700

Data Index: 774369 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 4.0432. Min Range: -4.0432

Max Act: 3.9200. Min Act: -0.1700

Data Index: 1251118 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 4.0432. Min Range: -4.0432

Max Act: 3.9165. Min Act: -0.1700

Data Index: 1236267 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 4.0432. Min Range: -4.0432

Max Act: 3.8781. Min Act: -0.1700

Data Index: 496925 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 4.0432. Min Range: -4.0432

Max Act: 3.9008. Min Act: -0.1700

Data Index: 391141 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 4.0432. Min Range: -4.0432

Max Act: 3.8866. Min Act: -0.1700

Data Index: 527575 (C4 (Web Text))

Max Activating Token Index: 283

Text #17

Max Range: 4.0432. Min Range: -4.0432

Max Act: 3.8862. Min Act: -0.1700

Data Index: 1052359 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 4.0432. Min Range: -4.0432

Max Act: 3.8791. Min Act: -0.1700

Data Index: 522811 (C4 (Web Text))

Max Activating Token Index: 418

Text #19

Max Range: 4.0432. Min Range: -4.0432

Max Act: 3.8799. Min Act: -0.1700

Data Index: 468166 (C4 (Web Text))

Max Activating Token Index: 36