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

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

Neuron 129 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: 3.3520. Min Range: -3.3520

Max Act: 3.3520. Min Act: -0.1700

Data Index: 76657 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 3.3520. Min Range: -3.3520

Max Act: 3.2735. Min Act: -0.1700

Data Index: 931117 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 3.3520. Min Range: -3.3520

Max Act: 3.2420. Min Act: -0.1700

Data Index: 914635 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 3.3520. Min Range: -3.3520

Max Act: 3.2420. Min Act: -0.1700

Data Index: 395830 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 3.3520. Min Range: -3.3520

Max Act: 3.2420. Min Act: -0.1700

Data Index: 1141913 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 3.3520. Min Range: -3.3520

Max Act: 3.2420. Min Act: -0.1700

Data Index: 1195575 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 3.3520. Min Range: -3.3520

Max Act: 3.2263. Min Act: -0.1700

Data Index: 683836 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 3.3520. Min Range: -3.3520

Max Act: 3.2263. Min Act: -0.1700

Data Index: 1290353 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 3.3520. Min Range: -3.3520

Max Act: 3.2420. Min Act: -0.1700

Data Index: 926963 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 3.3520. Min Range: -3.3520

Max Act: 3.2420. Min Act: -0.1700

Data Index: 1134916 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 3.3520. Min Range: -3.3520

Max Act: 3.2106. Min Act: -0.1700

Data Index: 448156 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 3.3520. Min Range: -3.3520

Max Act: 3.2106. Min Act: -0.1700

Data Index: 986336 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 3.3520. Min Range: -3.3520

Max Act: 3.2106. Min Act: -0.1700

Data Index: 1076857 (C4 (Web Text))

Max Activating Token Index: 3

Text #13

Max Range: 3.3520. Min Range: -3.3520

Max Act: 3.2106. Min Act: -0.1700

Data Index: 880140 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 3.3520. Min Range: -3.3520

Max Act: 3.1791. Min Act: -0.1700

Data Index: 460178 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 3.3520. Min Range: -3.3520

Max Act: 3.1949. Min Act: -0.1700

Data Index: 589070 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 3.3520. Min Range: -3.3520

Max Act: 3.1949. Min Act: -0.1700

Data Index: 526049 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 3.3520. Min Range: -3.3520

Max Act: 3.1949. Min Act: -0.1700

Data Index: 656641 (C4 (Web Text))

Max Activating Token Index: 187

Text #18

Max Range: 3.3520. Min Range: -3.3520

Max Act: 3.1791. Min Act: -0.1700

Data Index: 469959 (C4 (Web Text))

Max Activating Token Index: 306

Text #19

Max Range: 3.3520. Min Range: -3.3520

Max Act: 3.1949. Min Act: -0.1700

Data Index: 1148498 (C4 (Web Text))

Max Activating Token Index: 739