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

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

Neuron 97 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: 3.7654. Min Range: -3.7654

Max Act: 3.7654. Min Act: -0.1700

Data Index: 452107 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 3.7654. Min Range: -3.7654

Max Act: 3.7527. Min Act: -0.1700

Data Index: 448186 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 3.7654. Min Range: -3.7654

Max Act: 3.7163. Min Act: -0.1700

Data Index: 1290768 (C4 (Web Text))

Max Activating Token Index: 456

Text #3

Max Range: 3.7654. Min Range: -3.7654

Max Act: 3.6984. Min Act: -0.1700

Data Index: 33521 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 3.7654. Min Range: -3.7654

Max Act: 3.7082. Min Act: -0.1700

Data Index: 226119 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 3.7654. Min Range: -3.7654

Max Act: 3.6860. Min Act: -0.1700

Data Index: 1115476 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 3.7654. Min Range: -3.7654

Max Act: 3.7002. Min Act: -0.1700

Data Index: 1326640 (C4 (Web Text))

Max Activating Token Index: 530

Text #7

Max Range: 3.7654. Min Range: -3.7654

Max Act: 3.6951. Min Act: -0.1671

Data Index: 68793 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 3.7654. Min Range: -3.7654

Max Act: 3.6649. Min Act: -0.1696

Data Index: 1244998 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 3.7654. Min Range: -3.7654

Max Act: 3.6631. Min Act: -0.1699

Data Index: 736958 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 3.7654. Min Range: -3.7654

Max Act: 3.6460. Min Act: -0.1700

Data Index: 909575 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 3.7654. Min Range: -3.7654

Max Act: 3.6404. Min Act: -0.1699

Data Index: 892718 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 3.7654. Min Range: -3.7654

Max Act: 3.6250. Min Act: -0.1700

Data Index: 753413 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 3.7654. Min Range: -3.7654

Max Act: 3.6277. Min Act: -0.1700

Data Index: 326522 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 3.7654. Min Range: -3.7654

Max Act: 3.6279. Min Act: -0.1700

Data Index: 569291 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 3.7654. Min Range: -3.7654

Max Act: 3.6128. Min Act: -0.1700

Data Index: 539718 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 3.7654. Min Range: -3.7654

Max Act: 3.6141. Min Act: -0.1699

Data Index: 865272 (C4 (Web Text))

Max Activating Token Index: 445

Text #17

Max Range: 3.7654. Min Range: -3.7654

Max Act: 3.6123. Min Act: -0.1699

Data Index: 427935 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 3.7654. Min Range: -3.7654

Max Act: 3.5960. Min Act: -0.1697

Data Index: 1130405 (C4 (Web Text))

Max Activating Token Index: 724

Text #19

Max Range: 3.7654. Min Range: -3.7654

Max Act: 3.6091. Min Act: -0.1700

Data Index: 1202783 (C4 (Web Text))

Max Activating Token Index: 997