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

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

Neuron 1503 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4229. Min Range: -3.4229

Max Act: 3.4229. Min Act: -0.1700

Data Index: 343085 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 3.4229. Min Range: -3.4229

Max Act: 3.3601. Min Act: -0.1700

Data Index: 1295241 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 3.4229. Min Range: -3.4229

Max Act: 3.3287. Min Act: -0.1700

Data Index: 1103404 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 3.4229. Min Range: -3.4229

Max Act: 3.2973. Min Act: -0.1700

Data Index: 170958 (C4 (Web Text))

Max Activating Token Index: 310

Text #4

Max Range: 3.4229. Min Range: -3.4229

Max Act: 3.2816. Min Act: -0.1700

Data Index: 975996 (C4 (Web Text))

Max Activating Token Index: 70

Text #5

Max Range: 3.4229. Min Range: -3.4229

Max Act: 3.2659. Min Act: -0.1700

Data Index: 65003 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 3.4229. Min Range: -3.4229

Max Act: 3.2816. Min Act: -0.1700

Data Index: 1159448 (C4 (Web Text))

Max Activating Token Index: 809

Text #7

Max Range: 3.4229. Min Range: -3.4229

Max Act: 3.2502. Min Act: -0.1700

Data Index: 867273 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 3.4229. Min Range: -3.4229

Max Act: 3.2502. Min Act: -0.1700

Data Index: 1340348 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 3.4229. Min Range: -3.4229

Max Act: 3.2030. Min Act: -0.1700

Data Index: 934362 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 3.4229. Min Range: -3.4229

Max Act: 3.2030. Min Act: -0.1700

Data Index: 1343649 (C4 (Web Text))

Max Activating Token Index: 495

Text #11

Max Range: 3.4229. Min Range: -3.4229

Max Act: 3.2188. Min Act: -0.1700

Data Index: 1348854 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 3.4229. Min Range: -3.4229

Max Act: 3.2030. Min Act: -0.1700

Data Index: 822960 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 3.4229. Min Range: -3.4229

Max Act: 3.2188. Min Act: -0.1700

Data Index: 1013212 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 3.4229. Min Range: -3.4229

Max Act: 3.2030. Min Act: -0.1700

Data Index: 1358792 (C4 (Web Text))

Max Activating Token Index: 311

Text #15

Max Range: 3.4229. Min Range: -3.4229

Max Act: 3.2030. Min Act: -0.1700

Data Index: 666702 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 3.4229. Min Range: -3.4229

Max Act: 3.2030. Min Act: -0.1700

Data Index: 1142372 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 3.4229. Min Range: -3.4229

Max Act: 3.2188. Min Act: -0.1700

Data Index: 891512 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 3.4229. Min Range: -3.4229

Max Act: 3.2030. Min Act: -0.1700

Data Index: 640144 (C4 (Web Text))

Max Activating Token Index: 806

Text #19

Max Range: 3.4229. Min Range: -3.4229

Max Act: 3.1873. Min Act: -0.1700

Data Index: 399379 (C4 (Web Text))

Max Activating Token Index: 155