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

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

Neuron 1379 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6150. Min Range: -3.6150

Max Act: 3.6150. Min Act: -0.1700

Data Index: 1483328 (Python Code)

Max Activating Token Index: 817

Text #1

Max Range: 3.6150. Min Range: -3.6150

Max Act: 3.6150. Min Act: -0.1700

Data Index: 1423316 (Python Code)

Max Activating Token Index: 77

Text #2

Max Range: 3.6150. Min Range: -3.6150

Max Act: 3.4427. Min Act: -0.1700

Data Index: 1434961 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 3.6150. Min Range: -3.6150

Max Act: 3.3329. Min Act: -0.1700

Data Index: 550709 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 3.6150. Min Range: -3.6150

Max Act: 3.3015. Min Act: -0.1700

Data Index: 1613923 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 3.6150. Min Range: -3.6150

Max Act: 3.2858. Min Act: -0.1700

Data Index: 1342528 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 3.6150. Min Range: -3.6150

Max Act: 3.2700. Min Act: -0.1700

Data Index: 34057 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 3.6150. Min Range: -3.6150

Max Act: 3.2700. Min Act: -0.1700

Data Index: 139546 (C4 (Web Text))

Max Activating Token Index: 714

Text #8

Max Range: 3.6150. Min Range: -3.6150

Max Act: 3.2543. Min Act: -0.1700

Data Index: 187088 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 3.6150. Min Range: -3.6150

Max Act: 3.1914. Min Act: -0.1700

Data Index: 1491410 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 3.6150. Min Range: -3.6150

Max Act: 3.1599. Min Act: -0.1700

Data Index: 950430 (C4 (Web Text))

Max Activating Token Index: 966

Text #11

Max Range: 3.6150. Min Range: -3.6150

Max Act: 3.2386. Min Act: -0.1700

Data Index: 1357104 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 3.6150. Min Range: -3.6150

Max Act: 3.1914. Min Act: -0.1700

Data Index: 168957 (C4 (Web Text))

Max Activating Token Index: 787

Text #13

Max Range: 3.6150. Min Range: -3.6150

Max Act: 3.1757. Min Act: -0.1700

Data Index: 839178 (C4 (Web Text))

Max Activating Token Index: 427

Text #14

Max Range: 3.6150. Min Range: -3.6150

Max Act: 3.1914. Min Act: -0.1700

Data Index: 23288 (C4 (Web Text))

Max Activating Token Index: 664

Text #15

Max Range: 3.6150. Min Range: -3.6150

Max Act: 3.1599. Min Act: -0.1700

Data Index: 555399 (C4 (Web Text))

Max Activating Token Index: 157

Text #16

Max Range: 3.6150. Min Range: -3.6150

Max Act: 3.1757. Min Act: -0.1700

Data Index: 403547 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 3.6150. Min Range: -3.6150

Max Act: 3.1599. Min Act: -0.1700

Data Index: 1311773 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 3.6150. Min Range: -3.6150

Max Act: 3.1284. Min Act: -0.1700

Data Index: 996225 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 3.6150. Min Range: -3.6150

Max Act: 3.1442. Min Act: -0.1700

Data Index: 1337451 (C4 (Web Text))

Max Activating Token Index: 827