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

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

Neuron 262 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: 4.4787. Min Range: -4.4787

Max Act: 4.4740. Min Act: -0.1700

Data Index: 494133 (C4 (Web Text))

Max Activating Token Index: 403

Text #1

Max Range: 4.4787. Min Range: -4.4787

Max Act: 4.4787. Min Act: -0.1700

Data Index: 567056 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 4.4787. Min Range: -4.4787

Max Act: 4.2629. Min Act: -0.1700

Data Index: 918387 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 4.4787. Min Range: -4.4787

Max Act: 4.2216. Min Act: -0.1700

Data Index: 570511 (C4 (Web Text))

Max Activating Token Index: 637

Text #4

Max Range: 4.4787. Min Range: -4.4787

Max Act: 4.2198. Min Act: -0.1700

Data Index: 1129534 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 4.4787. Min Range: -4.4787

Max Act: 4.1828. Min Act: -0.1700

Data Index: 955247 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 4.4787. Min Range: -4.4787

Max Act: 4.2017. Min Act: -0.1700

Data Index: 397410 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 4.4787. Min Range: -4.4787

Max Act: 4.1916. Min Act: -0.1700

Data Index: 281217 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 4.4787. Min Range: -4.4787

Max Act: 4.1612. Min Act: -0.1697

Data Index: 264269 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 4.4787. Min Range: -4.4787

Max Act: 4.1734. Min Act: -0.1697

Data Index: 877587 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 4.4787. Min Range: -4.4787

Max Act: 4.1505. Min Act: -0.1700

Data Index: 1257137 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 4.4787. Min Range: -4.4787

Max Act: 4.1349. Min Act: -0.1700

Data Index: 701958 (C4 (Web Text))

Max Activating Token Index: 623

Text #12

Max Range: 4.4787. Min Range: -4.4787

Max Act: 4.1178. Min Act: -0.1700

Data Index: 1099125 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 4.4787. Min Range: -4.4787

Max Act: 4.1062. Min Act: -0.1697

Data Index: 613244 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 4.4787. Min Range: -4.4787

Max Act: 4.0894. Min Act: -0.1697

Data Index: 1020352 (C4 (Web Text))

Max Activating Token Index: 736

Text #15

Max Range: 4.4787. Min Range: -4.4787

Max Act: 4.0916. Min Act: -0.1697

Data Index: 1180979 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 4.4787. Min Range: -4.4787

Max Act: 4.0967. Min Act: -0.1700

Data Index: 93604 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 4.4787. Min Range: -4.4787

Max Act: 4.0620. Min Act: -0.1700

Data Index: 1108016 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 4.4787. Min Range: -4.4787

Max Act: 4.0760. Min Act: -0.1697

Data Index: 625310 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 4.4787. Min Range: -4.4787

Max Act: 4.0792. Min Act: -0.1700

Data Index: 814548 (C4 (Web Text))

Max Activating Token Index: 817