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

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

Neuron 1924 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: 3.9102. Min Range: -3.9102

Max Act: 3.9102. Min Act: -0.1700

Data Index: 1085490 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 3.9102. Min Range: -3.9102

Max Act: 3.8569. Min Act: -0.1700

Data Index: 1006545 (C4 (Web Text))

Max Activating Token Index: 659

Text #2

Max Range: 3.9102. Min Range: -3.9102

Max Act: 3.8623. Min Act: -0.1699

Data Index: 39792 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 3.9102. Min Range: -3.9102

Max Act: 3.8362. Min Act: -0.1700

Data Index: 679731 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 3.9102. Min Range: -3.9102

Max Act: 3.8084. Min Act: -0.1700

Data Index: 1170842 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 3.9102. Min Range: -3.9102

Max Act: 3.7980. Min Act: -0.1700

Data Index: 1070085 (C4 (Web Text))

Max Activating Token Index: 897

Text #6

Max Range: 3.9102. Min Range: -3.9102

Max Act: 3.8032. Min Act: -0.1700

Data Index: 148234 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 3.9102. Min Range: -3.9102

Max Act: 3.7910. Min Act: -0.1700

Data Index: 717668 (C4 (Web Text))

Max Activating Token Index: 351

Text #8

Max Range: 3.9102. Min Range: -3.9102

Max Act: 3.8047. Min Act: -0.1700

Data Index: 619354 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 3.9102. Min Range: -3.9102

Max Act: 3.7339. Min Act: -0.1700

Data Index: 1451496 (Python Code)

Max Activating Token Index: 314

Text #10

Max Range: 3.9102. Min Range: -3.9102

Max Act: 3.7405. Min Act: -0.1700

Data Index: 1177380 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 3.9102. Min Range: -3.9102

Max Act: 3.7337. Min Act: -0.1700

Data Index: 1245701 (C4 (Web Text))

Max Activating Token Index: 955

Text #12

Max Range: 3.9102. Min Range: -3.9102

Max Act: 3.7050. Min Act: -0.1700

Data Index: 852597 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 3.9102. Min Range: -3.9102

Max Act: 3.7221. Min Act: -0.1699

Data Index: 30782 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 3.9102. Min Range: -3.9102

Max Act: 3.6993. Min Act: -0.1700

Data Index: 944515 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 3.9102. Min Range: -3.9102

Max Act: 3.7072. Min Act: -0.1700

Data Index: 1409762 (Python Code)

Max Activating Token Index: 433

Text #16

Max Range: 3.9102. Min Range: -3.9102

Max Act: 3.6877. Min Act: -0.1700

Data Index: 1010927 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 3.9102. Min Range: -3.9102

Max Act: 3.6940. Min Act: -0.1700

Data Index: 1452220 (Python Code)

Max Activating Token Index: 966

Text #18

Max Range: 3.9102. Min Range: -3.9102

Max Act: 3.6932. Min Act: -0.1700

Data Index: 957179 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 3.9102. Min Range: -3.9102

Max Act: 3.6748. Min Act: -0.1700

Data Index: 782634 (C4 (Web Text))

Max Activating Token Index: 807