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

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

Neuron 436 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: 3.7434. Min Range: -3.7434

Max Act: 3.7434. Min Act: -0.1700

Data Index: 185045 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 3.7434. Min Range: -3.7434

Max Act: 3.6438. Min Act: -0.1700

Data Index: 417018 (C4 (Web Text))

Max Activating Token Index: 425

Text #2

Max Range: 3.7434. Min Range: -3.7434

Max Act: 3.5801. Min Act: -0.1700

Data Index: 1653312 (Python Code)

Max Activating Token Index: 485

Text #3

Max Range: 3.7434. Min Range: -3.7434

Max Act: 3.5679. Min Act: -0.1700

Data Index: 584223 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 3.7434. Min Range: -3.7434

Max Act: 3.5582. Min Act: -0.1700

Data Index: 196726 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 3.7434. Min Range: -3.7434

Max Act: 3.5128. Min Act: -0.1700

Data Index: 1086888 (C4 (Web Text))

Max Activating Token Index: 635

Text #6

Max Range: 3.7434. Min Range: -3.7434

Max Act: 3.4635. Min Act: -0.1700

Data Index: 1482342 (Python Code)

Max Activating Token Index: 955

Text #7

Max Range: 3.7434. Min Range: -3.7434

Max Act: 3.5157. Min Act: -0.1700

Data Index: 1309165 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 3.7434. Min Range: -3.7434

Max Act: 3.5022. Min Act: -0.1700

Data Index: 579751 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 3.7434. Min Range: -3.7434

Max Act: 3.4840. Min Act: -0.1700

Data Index: 1342377 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 3.7434. Min Range: -3.7434

Max Act: 3.4873. Min Act: -0.1700

Data Index: 745769 (C4 (Web Text))

Max Activating Token Index: 515

Text #11

Max Range: 3.7434. Min Range: -3.7434

Max Act: 3.4945. Min Act: -0.1700

Data Index: 883563 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 3.7434. Min Range: -3.7434

Max Act: 3.4864. Min Act: -0.1700

Data Index: 147503 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 3.7434. Min Range: -3.7434

Max Act: 3.4672. Min Act: -0.1700

Data Index: 1013510 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 3.7434. Min Range: -3.7434

Max Act: 3.4754. Min Act: -0.1700

Data Index: 1046324 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 3.7434. Min Range: -3.7434

Max Act: 3.4764. Min Act: -0.1700

Data Index: 1034787 (C4 (Web Text))

Max Activating Token Index: 173

Text #16

Max Range: 3.7434. Min Range: -3.7434

Max Act: 3.4902. Min Act: -0.1700

Data Index: 730263 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 3.7434. Min Range: -3.7434

Max Act: 3.4707. Min Act: -0.1700

Data Index: 924960 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 3.7434. Min Range: -3.7434

Max Act: 3.4575. Min Act: -0.1700

Data Index: 720500 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 3.7434. Min Range: -3.7434

Max Act: 3.4807. Min Act: -0.1700

Data Index: 1332864 (C4 (Web Text))

Max Activating Token Index: 996