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

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

Neuron 1328 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: 3.4707. Min Range: -3.4707

Max Act: 3.4707. Min Act: -0.1110

Data Index: 1485894 (Python Code)

Max Activating Token Index: 1022

Text #1

Max Range: 3.4707. Min Range: -3.4707

Max Act: 3.4077. Min Act: 0.0814

Data Index: 997597 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 3.4707. Min Range: -3.4707

Max Act: 3.4098. Min Act: 0.2494

Data Index: 1392326 (Python Code)

Max Activating Token Index: 274

Text #3

Max Range: 3.4707. Min Range: -3.4707

Max Act: 3.3803. Min Act: -0.1583

Data Index: 24893 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 3.4707. Min Range: -3.4707

Max Act: 3.3787. Min Act: -0.1698

Data Index: 372125 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 3.4707. Min Range: -3.4707

Max Act: 3.3950. Min Act: -0.1477

Data Index: 1044956 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 3.4707. Min Range: -3.4707

Max Act: 3.3889. Min Act: -0.1697

Data Index: 1187091 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 3.4707. Min Range: -3.4707

Max Act: 3.3788. Min Act: -0.0890

Data Index: 905251 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 3.4707. Min Range: -3.4707

Max Act: 3.3743. Min Act: 0.5041

Data Index: 1616733 (Python Code)

Max Activating Token Index: 554

Text #9

Max Range: 3.4707. Min Range: -3.4707

Max Act: 3.3545. Min Act: -0.0258

Data Index: 1372587 (Python Code)

Max Activating Token Index: 464

Text #10

Max Range: 3.4707. Min Range: -3.4707

Max Act: 3.3308. Min Act: -0.1478

Data Index: 1453018 (Python Code)

Max Activating Token Index: 847

Text #11

Max Range: 3.4707. Min Range: -3.4707

Max Act: 3.3221. Min Act: -0.1699

Data Index: 333197 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 3.4707. Min Range: -3.4707

Max Act: 3.3053. Min Act: -0.1617

Data Index: 484197 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 3.4707. Min Range: -3.4707

Max Act: 3.3135. Min Act: -0.1664

Data Index: 310383 (C4 (Web Text))

Max Activating Token Index: 731

Text #14

Max Range: 3.4707. Min Range: -3.4707

Max Act: 3.3041. Min Act: -0.1591

Data Index: 836181 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 3.4707. Min Range: -3.4707

Max Act: 3.2893. Min Act: -0.1699

Data Index: 1309233 (C4 (Web Text))

Max Activating Token Index: 234

Text #16

Max Range: 3.4707. Min Range: -3.4707

Max Act: 3.2943. Min Act: -0.0263

Data Index: 1557158 (Python Code)

Max Activating Token Index: 405

Text #17

Max Range: 3.4707. Min Range: -3.4707

Max Act: 3.2938. Min Act: -0.0935

Data Index: 1363414 (Python Code)

Max Activating Token Index: 278

Text #18

Max Range: 3.4707. Min Range: -3.4707

Max Act: 3.2926. Min Act: -0.1016

Data Index: 1644301 (Python Code)

Max Activating Token Index: 899

Text #19

Max Range: 3.4707. Min Range: -3.4707

Max Act: 3.2658. Min Act: -0.1609

Data Index: 1028916 (C4 (Web Text))

Max Activating Token Index: 223