Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1618 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.4059. Min Range: -5.4059

Max Act: 5.4059. Min Act: -0.1700

Data Index: 1207583 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 5.4059. Min Range: -5.4059

Max Act: 5.3434. Min Act: -0.1700

Data Index: 502902 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 5.4059. Min Range: -5.4059

Max Act: 5.3122. Min Act: -0.1700

Data Index: 195542 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 5.4059. Min Range: -5.4059

Max Act: 5.2809. Min Act: -0.1700

Data Index: 984534 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 5.4059. Min Range: -5.4059

Max Act: 5.2809. Min Act: -0.1700

Data Index: 788844 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 5.4059. Min Range: -5.4059

Max Act: 5.2497. Min Act: -0.1700

Data Index: 306484 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 5.4059. Min Range: -5.4059

Max Act: 5.2184. Min Act: -0.1700

Data Index: 949251 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 5.4059. Min Range: -5.4059

Max Act: 5.2809. Min Act: -0.1700

Data Index: 260734 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 5.4059. Min Range: -5.4059

Max Act: 5.2497. Min Act: -0.1700

Data Index: 18985 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 5.4059. Min Range: -5.4059

Max Act: 5.1872. Min Act: -0.1700

Data Index: 614014 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 5.4059. Min Range: -5.4059

Max Act: 5.2184. Min Act: -0.1700

Data Index: 751737 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 5.4059. Min Range: -5.4059

Max Act: 5.1872. Min Act: -0.1700

Data Index: 1295268 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 5.4059. Min Range: -5.4059

Max Act: 5.1872. Min Act: -0.1700

Data Index: 579519 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 5.4059. Min Range: -5.4059

Max Act: 5.1872. Min Act: -0.1700

Data Index: 211680 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 5.4059. Min Range: -5.4059

Max Act: 5.1872. Min Act: -0.1700

Data Index: 1312111 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 5.4059. Min Range: -5.4059

Max Act: 5.1872. Min Act: -0.1700

Data Index: 1119879 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 5.4059. Min Range: -5.4059

Max Act: 5.1247. Min Act: -0.1700

Data Index: 222512 (C4 (Web Text))

Max Activating Token Index: 192

Text #17

Max Range: 5.4059. Min Range: -5.4059

Max Act: 5.1872. Min Act: -0.1700

Data Index: 14667 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 5.4059. Min Range: -5.4059

Max Act: 5.1247. Min Act: -0.1700

Data Index: 1159819 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 5.4059. Min Range: -5.4059

Max Act: 5.1247. Min Act: -0.1700

Data Index: 339128 (C4 (Web Text))

Max Activating Token Index: 641