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

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

Neuron 57 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: 3.9423. Min Range: -3.9423

Max Act: 3.9423. Min Act: -0.1700

Data Index: 165671 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 3.9423. Min Range: -3.9423

Max Act: 3.8922. Min Act: -0.1700

Data Index: 742237 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 3.9423. Min Range: -3.9423

Max Act: 3.9238. Min Act: -0.1700

Data Index: 371118 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 3.9423. Min Range: -3.9423

Max Act: 3.9146. Min Act: -0.1700

Data Index: 106385 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 3.9423. Min Range: -3.9423

Max Act: 3.8510. Min Act: -0.1700

Data Index: 604759 (C4 (Web Text))

Max Activating Token Index: 819

Text #5

Max Range: 3.9423. Min Range: -3.9423

Max Act: 3.8490. Min Act: -0.1700

Data Index: 867024 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 3.9423. Min Range: -3.9423

Max Act: 3.8210. Min Act: -0.1700

Data Index: 776235 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 3.9423. Min Range: -3.9423

Max Act: 3.8467. Min Act: -0.1700

Data Index: 220436 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 3.9423. Min Range: -3.9423

Max Act: 3.8638. Min Act: -0.1700

Data Index: 384178 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 3.9423. Min Range: -3.9423

Max Act: 3.8635. Min Act: -0.1700

Data Index: 303593 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 3.9423. Min Range: -3.9423

Max Act: 3.8673. Min Act: -0.1700

Data Index: 413257 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 3.9423. Min Range: -3.9423

Max Act: 3.8287. Min Act: -0.1700

Data Index: 683217 (C4 (Web Text))

Max Activating Token Index: 621

Text #12

Max Range: 3.9423. Min Range: -3.9423

Max Act: 3.8287. Min Act: -0.1700

Data Index: 1337340 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 3.9423. Min Range: -3.9423

Max Act: 3.7914. Min Act: -0.1700

Data Index: 245810 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 3.9423. Min Range: -3.9423

Max Act: 3.8003. Min Act: -0.1700

Data Index: 1090164 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 3.9423. Min Range: -3.9423

Max Act: 3.8059. Min Act: -0.1700

Data Index: 801791 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 3.9423. Min Range: -3.9423

Max Act: 3.8267. Min Act: -0.1700

Data Index: 744647 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 3.9423. Min Range: -3.9423

Max Act: 3.8186. Min Act: -0.1700

Data Index: 91299 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 3.9423. Min Range: -3.9423

Max Act: 3.8271. Min Act: -0.1700

Data Index: 349188 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 3.9423. Min Range: -3.9423

Max Act: 3.8020. Min Act: -0.1700

Data Index: 714338 (C4 (Web Text))

Max Activating Token Index: 300