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

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

Neuron 562 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: 2.8622. Min Range: -2.8622

Max Act: 2.8622. Min Act: -0.1700

Data Index: 455742 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 2.8622. Min Range: -2.8622

Max Act: 2.8340. Min Act: -0.1700

Data Index: 1598791 (Python Code)

Max Activating Token Index: 12

Text #2

Max Range: 2.8622. Min Range: -2.8622

Max Act: 2.7596. Min Act: -0.1700

Data Index: 388056 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 2.8622. Min Range: -2.8622

Max Act: 2.7614. Min Act: -0.1700

Data Index: 1135111 (C4 (Web Text))

Max Activating Token Index: 475

Text #4

Max Range: 2.8622. Min Range: -2.8622

Max Act: 2.7424. Min Act: -0.1700

Data Index: 86405 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 2.8622. Min Range: -2.8622

Max Act: 2.7423. Min Act: -0.1700

Data Index: 1004491 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 2.8622. Min Range: -2.8622

Max Act: 2.7199. Min Act: -0.1700

Data Index: 1604426 (Python Code)

Max Activating Token Index: 427

Text #7

Max Range: 2.8622. Min Range: -2.8622

Max Act: 2.7107. Min Act: -0.1700

Data Index: 537085 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 2.8622. Min Range: -2.8622

Max Act: 2.7062. Min Act: -0.1700

Data Index: 497965 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 2.8622. Min Range: -2.8622

Max Act: 2.7186. Min Act: -0.1700

Data Index: 751752 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 2.8622. Min Range: -2.8622

Max Act: 2.6653. Min Act: -0.1700

Data Index: 804503 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 2.8622. Min Range: -2.8622

Max Act: 2.7090. Min Act: -0.1700

Data Index: 1467064 (Python Code)

Max Activating Token Index: 402

Text #12

Max Range: 2.8622. Min Range: -2.8622

Max Act: 2.6775. Min Act: -0.1700

Data Index: 390847 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 2.8622. Min Range: -2.8622

Max Act: 2.6578. Min Act: -0.1700

Data Index: 206184 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 2.8622. Min Range: -2.8622

Max Act: 2.6662. Min Act: -0.1700

Data Index: 6346 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 2.8622. Min Range: -2.8622

Max Act: 2.6514. Min Act: -0.1700

Data Index: 927690 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 2.8622. Min Range: -2.8622

Max Act: 2.6478. Min Act: -0.1700

Data Index: 1049264 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 2.8622. Min Range: -2.8622

Max Act: 2.6646. Min Act: -0.1700

Data Index: 332115 (C4 (Web Text))

Max Activating Token Index: 354

Text #18

Max Range: 2.8622. Min Range: -2.8622

Max Act: 2.6371. Min Act: -0.1700

Data Index: 133077 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 2.8622. Min Range: -2.8622

Max Act: 2.6715. Min Act: -0.1700

Data Index: 47146 (C4 (Web Text))

Max Activating Token Index: 559