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

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

Neuron 429 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: 2.9746. Min Range: -2.9746

Max Act: 2.9746. Min Act: -0.1700

Data Index: 329271 (C4 (Web Text))

Max Activating Token Index: 406

Text #1

Max Range: 2.9746. Min Range: -2.9746

Max Act: 2.9497. Min Act: -0.1700

Data Index: 971295 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 2.9746. Min Range: -2.9746

Max Act: 2.9182. Min Act: -0.1700

Data Index: 1201887 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 2.9746. Min Range: -2.9746

Max Act: 2.8969. Min Act: -0.1700

Data Index: 1119356 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 2.9746. Min Range: -2.9746

Max Act: 2.9130. Min Act: -0.1700

Data Index: 1053208 (C4 (Web Text))

Max Activating Token Index: 928

Text #5

Max Range: 2.9746. Min Range: -2.9746

Max Act: 2.9238. Min Act: -0.1700

Data Index: 979920 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 2.9746. Min Range: -2.9746

Max Act: 2.9086. Min Act: -0.1700

Data Index: 899803 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 2.9746. Min Range: -2.9746

Max Act: 2.8945. Min Act: -0.1700

Data Index: 884147 (C4 (Web Text))

Max Activating Token Index: 321

Text #8

Max Range: 2.9746. Min Range: -2.9746

Max Act: 2.8894. Min Act: -0.1700

Data Index: 1155398 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 2.9746. Min Range: -2.9746

Max Act: 2.8755. Min Act: -0.1700

Data Index: 1197477 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 2.9746. Min Range: -2.9746

Max Act: 2.8933. Min Act: -0.1700

Data Index: 771899 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 2.9746. Min Range: -2.9746

Max Act: 2.8442. Min Act: -0.1700

Data Index: 474880 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 2.9746. Min Range: -2.9746

Max Act: 2.8759. Min Act: -0.1700

Data Index: 952029 (C4 (Web Text))

Max Activating Token Index: 433

Text #13

Max Range: 2.9746. Min Range: -2.9746

Max Act: 2.8571. Min Act: -0.1700

Data Index: 504795 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 2.9746. Min Range: -2.9746

Max Act: 2.8556. Min Act: -0.1700

Data Index: 502088 (C4 (Web Text))

Max Activating Token Index: 799

Text #15

Max Range: 2.9746. Min Range: -2.9746

Max Act: 2.8469. Min Act: -0.1700

Data Index: 668297 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 2.9746. Min Range: -2.9746

Max Act: 2.8540. Min Act: -0.1700

Data Index: 785212 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 2.9746. Min Range: -2.9746

Max Act: 2.8209. Min Act: -0.1700

Data Index: 311301 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 2.9746. Min Range: -2.9746

Max Act: 2.8465. Min Act: -0.1700

Data Index: 70798 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 2.9746. Min Range: -2.9746

Max Act: 2.8063. Min Act: -0.1700

Data Index: 557205 (C4 (Web Text))

Max Activating Token Index: 264