Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1593 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.3218. Min Range: -5.3218

Max Act: 5.3218. Min Act: -0.1700

Data Index: 713145 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 5.3218. Min Range: -5.3218

Max Act: 5.1968. Min Act: -0.1700

Data Index: 242941 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 5.3218. Min Range: -5.3218

Max Act: 5.2593. Min Act: -0.1700

Data Index: 1354881 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 5.3218. Min Range: -5.3218

Max Act: 5.2593. Min Act: -0.1700

Data Index: 1095316 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 5.3218. Min Range: -5.3218

Max Act: 5.2905. Min Act: -0.1700

Data Index: 143155 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 5.3218. Min Range: -5.3218

Max Act: 5.1968. Min Act: -0.1700

Data Index: 735023 (C4 (Web Text))

Max Activating Token Index: 220

Text #6

Max Range: 5.3218. Min Range: -5.3218

Max Act: 5.2280. Min Act: -0.1700

Data Index: 155641 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 5.3218. Min Range: -5.3218

Max Act: 5.1968. Min Act: -0.1700

Data Index: 221246 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 5.3218. Min Range: -5.3218

Max Act: 5.1655. Min Act: -0.1700

Data Index: 1454229 (Python Code)

Max Activating Token Index: 998

Text #9

Max Range: 5.3218. Min Range: -5.3218

Max Act: 5.2280. Min Act: -0.1700

Data Index: 1141335 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 5.3218. Min Range: -5.3218

Max Act: 5.1968. Min Act: -0.1700

Data Index: 334116 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 5.3218. Min Range: -5.3218

Max Act: 5.1655. Min Act: -0.1700

Data Index: 996497 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 5.3218. Min Range: -5.3218

Max Act: 5.2280. Min Act: -0.1700

Data Index: 955437 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 5.3218. Min Range: -5.3218

Max Act: 5.2280. Min Act: -0.1700

Data Index: 715111 (C4 (Web Text))

Max Activating Token Index: 555

Text #14

Max Range: 5.3218. Min Range: -5.3218

Max Act: 5.2280. Min Act: -0.1700

Data Index: 1038543 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 5.3218. Min Range: -5.3218

Max Act: 5.0718. Min Act: -0.1700

Data Index: 438281 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 5.3218. Min Range: -5.3218

Max Act: 5.2280. Min Act: -0.1700

Data Index: 642682 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 5.3218. Min Range: -5.3218

Max Act: 5.1655. Min Act: -0.1700

Data Index: 877778 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 5.3218. Min Range: -5.3218

Max Act: 5.1343. Min Act: -0.1700

Data Index: 526274 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 5.3218. Min Range: -5.3218

Max Act: 5.0718. Min Act: -0.1700

Data Index: 639352 (C4 (Web Text))

Max Activating Token Index: 694