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

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

Neuron 630 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: 3.4975. Min Range: -3.4975

Max Act: 3.4975. Min Act: -0.1700

Data Index: 1275816 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.4353. Min Act: -0.1700

Data Index: 1529568 (Python Code)

Max Activating Token Index: 652

Text #2

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.4016. Min Act: -0.1700

Data Index: 1164369 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.3553. Min Act: -0.1700

Data Index: 702609 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.3709. Min Act: -0.1700

Data Index: 913945 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.4060. Min Act: -0.1700

Data Index: 1187656 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.3934. Min Act: -0.1700

Data Index: 577146 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.3745. Min Act: -0.1700

Data Index: 324206 (C4 (Web Text))

Max Activating Token Index: 865

Text #8

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.3665. Min Act: -0.1700

Data Index: 653821 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.3880. Min Act: -0.1700

Data Index: 810801 (C4 (Web Text))

Max Activating Token Index: 897

Text #10

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.3682. Min Act: -0.1700

Data Index: 1169205 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.3952. Min Act: -0.1700

Data Index: 573616 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.3376. Min Act: -0.1700

Data Index: 402568 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.3508. Min Act: -0.1700

Data Index: 1197178 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.3625. Min Act: -0.1700

Data Index: 1054356 (C4 (Web Text))

Max Activating Token Index: 324

Text #15

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.3348. Min Act: -0.1700

Data Index: 1408658 (Python Code)

Max Activating Token Index: 279

Text #16

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.3555. Min Act: -0.1700

Data Index: 96704 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.3543. Min Act: -0.1700

Data Index: 917921 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.3430. Min Act: -0.1700

Data Index: 1347069 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.3258. Min Act: -0.1700

Data Index: 169745 (C4 (Web Text))

Max Activating Token Index: 51