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

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

Neuron 297 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: 3.9346. Min Range: -3.9346

Max Act: 3.9308. Min Act: -0.1700

Data Index: 114335 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.9346. Min Range: -3.9346

Max Act: 3.9346. Min Act: -0.1700

Data Index: 1644066 (Python Code)

Max Activating Token Index: 746

Text #2

Max Range: 3.9346. Min Range: -3.9346

Max Act: 3.9224. Min Act: -0.1700

Data Index: 566195 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.9346. Min Range: -3.9346

Max Act: 3.8785. Min Act: -0.1699

Data Index: 845071 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 3.9346. Min Range: -3.9346

Max Act: 3.8520. Min Act: -0.1687

Data Index: 762168 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 3.9346. Min Range: -3.9346

Max Act: 3.8596. Min Act: -0.1700

Data Index: 1493960 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 3.9346. Min Range: -3.9346

Max Act: 3.8461. Min Act: -0.0972

Data Index: 1550433 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 3.9346. Min Range: -3.9346

Max Act: 3.8470. Min Act: -0.1697

Data Index: 552220 (C4 (Web Text))

Max Activating Token Index: 561

Text #8

Max Range: 3.9346. Min Range: -3.9346

Max Act: 3.8336. Min Act: -0.1700

Data Index: 1387281 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 3.9346. Min Range: -3.9346

Max Act: 3.7939. Min Act: -0.0974

Data Index: 1209374 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.9346. Min Range: -3.9346

Max Act: 3.7706. Min Act: -0.1700

Data Index: 559445 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 3.9346. Min Range: -3.9346

Max Act: 3.7653. Min Act: -0.1700

Data Index: 1446338 (Python Code)

Max Activating Token Index: 316

Text #12

Max Range: 3.9346. Min Range: -3.9346

Max Act: 3.7496. Min Act: -0.1700

Data Index: 1090544 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 3.9346. Min Range: -3.9346

Max Act: 3.7635. Min Act: -0.1699

Data Index: 985162 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 3.9346. Min Range: -3.9346

Max Act: 3.7510. Min Act: -0.1353

Data Index: 1144792 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 3.9346. Min Range: -3.9346

Max Act: 3.7089. Min Act: -0.1700

Data Index: 944050 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 3.9346. Min Range: -3.9346

Max Act: 3.7329. Min Act: -0.1700

Data Index: 781242 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 3.9346. Min Range: -3.9346

Max Act: 3.7211. Min Act: -0.1031

Data Index: 1027310 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 3.9346. Min Range: -3.9346

Max Act: 3.6980. Min Act: -0.1699

Data Index: 29179 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 3.9346. Min Range: -3.9346

Max Act: 3.6831. Min Act: -0.1700

Data Index: 1471773 (Python Code)

Max Activating Token Index: 1023