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

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

Neuron 81 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: 3.2240. Min Range: -3.2240

Max Act: 3.2240. Min Act: -0.1700

Data Index: 813616 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 3.2240. Min Range: -3.2240

Max Act: 3.2240. Min Act: -0.1700

Data Index: 1086692 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 3.2240. Min Range: -3.2240

Max Act: 3.2240. Min Act: -0.1700

Data Index: 1159935 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 3.2240. Min Range: -3.2240

Max Act: 3.2083. Min Act: -0.1700

Data Index: 258258 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 3.2240. Min Range: -3.2240

Max Act: 3.1768. Min Act: -0.1700

Data Index: 143604 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 3.2240. Min Range: -3.2240

Max Act: 3.1453. Min Act: -0.1700

Data Index: 492713 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 3.2240. Min Range: -3.2240

Max Act: 3.1768. Min Act: -0.1700

Data Index: 1019818 (C4 (Web Text))

Max Activating Token Index: 293

Text #7

Max Range: 3.2240. Min Range: -3.2240

Max Act: 3.1610. Min Act: -0.1700

Data Index: 997969 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 3.2240. Min Range: -3.2240

Max Act: 3.1610. Min Act: -0.1700

Data Index: 987262 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 3.2240. Min Range: -3.2240

Max Act: 3.1768. Min Act: -0.1700

Data Index: 309510 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 3.2240. Min Range: -3.2240

Max Act: 3.1610. Min Act: -0.1700

Data Index: 223761 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 3.2240. Min Range: -3.2240

Max Act: 3.1453. Min Act: -0.1700

Data Index: 1052155 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 3.2240. Min Range: -3.2240

Max Act: 3.1453. Min Act: -0.1700

Data Index: 556958 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 3.2240. Min Range: -3.2240

Max Act: 3.1453. Min Act: -0.1700

Data Index: 36149 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 3.2240. Min Range: -3.2240

Max Act: 3.1610. Min Act: -0.1700

Data Index: 243876 (C4 (Web Text))

Max Activating Token Index: 398

Text #15

Max Range: 3.2240. Min Range: -3.2240

Max Act: 3.1453. Min Act: -0.1700

Data Index: 407000 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 3.2240. Min Range: -3.2240

Max Act: 3.1453. Min Act: -0.1700

Data Index: 418578 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 3.2240. Min Range: -3.2240

Max Act: 3.1610. Min Act: -0.1700

Data Index: 408771 (C4 (Web Text))

Max Activating Token Index: 6

Text #18

Max Range: 3.2240. Min Range: -3.2240

Max Act: 3.1610. Min Act: -0.1700

Data Index: 429621 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 3.2240. Min Range: -3.2240

Max Act: 3.1295. Min Act: -0.1700

Data Index: 1021800 (C4 (Web Text))

Max Activating Token Index: 417