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

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

Neuron 1242 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: 3.4169. Min Range: -3.4169

Max Act: 3.4169. Min Act: -0.1700

Data Index: 945842 (C4 (Web Text))

Max Activating Token Index: 401

Text #1

Max Range: 3.4169. Min Range: -3.4169

Max Act: 3.4169. Min Act: -0.1700

Data Index: 609841 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 3.4169. Min Range: -3.4169

Max Act: 3.2756. Min Act: -0.1700

Data Index: 321046 (C4 (Web Text))

Max Activating Token Index: 422

Text #3

Max Range: 3.4169. Min Range: -3.4169

Max Act: 3.2442. Min Act: -0.1700

Data Index: 623153 (C4 (Web Text))

Max Activating Token Index: 525

Text #4

Max Range: 3.4169. Min Range: -3.4169

Max Act: 3.2599. Min Act: -0.1700

Data Index: 1262344 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 3.4169. Min Range: -3.4169

Max Act: 3.1970. Min Act: -0.1700

Data Index: 921821 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 3.4169. Min Range: -3.4169

Max Act: 3.1970. Min Act: -0.1700

Data Index: 1271897 (C4 (Web Text))

Max Activating Token Index: 117

Text #7

Max Range: 3.4169. Min Range: -3.4169

Max Act: 3.1655. Min Act: -0.1700

Data Index: 1257912 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 3.4169. Min Range: -3.4169

Max Act: 3.1498. Min Act: -0.1700

Data Index: 860694 (C4 (Web Text))

Max Activating Token Index: 377

Text #9

Max Range: 3.4169. Min Range: -3.4169

Max Act: 3.1655. Min Act: -0.1700

Data Index: 1293881 (C4 (Web Text))

Max Activating Token Index: 238

Text #10

Max Range: 3.4169. Min Range: -3.4169

Max Act: 3.1340. Min Act: -0.1700

Data Index: 55528 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 3.4169. Min Range: -3.4169

Max Act: 3.1183. Min Act: -0.1700

Data Index: 1040576 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 3.4169. Min Range: -3.4169

Max Act: 3.1340. Min Act: -0.1700

Data Index: 552271 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 3.4169. Min Range: -3.4169

Max Act: 3.1340. Min Act: -0.1700

Data Index: 28224 (C4 (Web Text))

Max Activating Token Index: 895

Text #14

Max Range: 3.4169. Min Range: -3.4169

Max Act: 3.1183. Min Act: -0.1700

Data Index: 113764 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 3.4169. Min Range: -3.4169

Max Act: 3.1025. Min Act: -0.1700

Data Index: 953790 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 3.4169. Min Range: -3.4169

Max Act: 3.1025. Min Act: -0.1700

Data Index: 605082 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 3.4169. Min Range: -3.4169

Max Act: 3.1025. Min Act: -0.1700

Data Index: 77907 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 3.4169. Min Range: -3.4169

Max Act: 3.1183. Min Act: -0.1700

Data Index: 19305 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 3.4169. Min Range: -3.4169

Max Act: 3.1183. Min Act: -0.1700

Data Index: 308639 (C4 (Web Text))

Max Activating Token Index: 608