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

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

Neuron 42 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: 4.4106. Min Range: -4.4106

Max Act: 4.4106. Min Act: -0.1700

Data Index: 356593 (C4 (Web Text))

Max Activating Token Index: 516

Text #1

Max Range: 4.4106. Min Range: -4.4106

Max Act: 4.3770. Min Act: -0.1700

Data Index: 1554303 (Python Code)

Max Activating Token Index: 357

Text #2

Max Range: 4.4106. Min Range: -4.4106

Max Act: 4.3327. Min Act: -0.1700

Data Index: 153677 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 4.4106. Min Range: -4.4106

Max Act: 4.3208. Min Act: -0.1700

Data Index: 1549778 (Python Code)

Max Activating Token Index: 656

Text #4

Max Range: 4.4106. Min Range: -4.4106

Max Act: 4.2841. Min Act: -0.1700

Data Index: 1416354 (Python Code)

Max Activating Token Index: 283

Text #5

Max Range: 4.4106. Min Range: -4.4106

Max Act: 4.2715. Min Act: -0.1700

Data Index: 1389998 (Python Code)

Max Activating Token Index: 836

Text #6

Max Range: 4.4106. Min Range: -4.4106

Max Act: 4.2893. Min Act: -0.1700

Data Index: 1317491 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 4.4106. Min Range: -4.4106

Max Act: 4.2459. Min Act: -0.1700

Data Index: 229736 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 4.4106. Min Range: -4.4106

Max Act: 4.2371. Min Act: -0.1700

Data Index: 5804 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 4.4106. Min Range: -4.4106

Max Act: 4.2041. Min Act: -0.1700

Data Index: 1582924 (Python Code)

Max Activating Token Index: 537

Text #10

Max Range: 4.4106. Min Range: -4.4106

Max Act: 4.2084. Min Act: -0.1700

Data Index: 1641290 (Python Code)

Max Activating Token Index: 846

Text #11

Max Range: 4.4106. Min Range: -4.4106

Max Act: 4.1511. Min Act: -0.1700

Data Index: 1222031 (C4 (Web Text))

Max Activating Token Index: 890

Text #12

Max Range: 4.4106. Min Range: -4.4106

Max Act: 4.1847. Min Act: -0.1700

Data Index: 1382559 (Python Code)

Max Activating Token Index: 815

Text #13

Max Range: 4.4106. Min Range: -4.4106

Max Act: 4.1997. Min Act: -0.1700

Data Index: 810713 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 4.4106. Min Range: -4.4106

Max Act: 4.1725. Min Act: -0.1700

Data Index: 148404 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 4.4106. Min Range: -4.4106

Max Act: 4.1145. Min Act: -0.1700

Data Index: 1602761 (Python Code)

Max Activating Token Index: 267

Text #16

Max Range: 4.4106. Min Range: -4.4106

Max Act: 4.1256. Min Act: -0.1700

Data Index: 517424 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 4.4106. Min Range: -4.4106

Max Act: 4.1218. Min Act: -0.1700

Data Index: 20731 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 4.4106. Min Range: -4.4106

Max Act: 4.1224. Min Act: -0.1700

Data Index: 1537150 (Python Code)

Max Activating Token Index: 767

Text #19

Max Range: 4.4106. Min Range: -4.4106

Max Act: 4.1004. Min Act: -0.1700

Data Index: 779037 (C4 (Web Text))

Max Activating Token Index: 376