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

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

Neuron 1044 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8208. Min Range: -3.8208

Max Act: 3.8208. Min Act: -0.1700

Data Index: 701364 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 3.8208. Min Range: -3.8208

Max Act: 3.8208. Min Act: -0.1700

Data Index: 268185 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 3.8208. Min Range: -3.8208

Max Act: 3.7895. Min Act: -0.1700

Data Index: 682945 (C4 (Web Text))

Max Activating Token Index: 1010

Text #3

Max Range: 3.8208. Min Range: -3.8208

Max Act: 3.7895. Min Act: -0.1700

Data Index: 269734 (C4 (Web Text))

Max Activating Token Index: 762

Text #4

Max Range: 3.8208. Min Range: -3.8208

Max Act: 3.7582. Min Act: -0.1700

Data Index: 277509 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 3.8208. Min Range: -3.8208

Max Act: 3.7269. Min Act: -0.1700

Data Index: 351186 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 3.8208. Min Range: -3.8208

Max Act: 3.7582. Min Act: -0.1700

Data Index: 1293283 (C4 (Web Text))

Max Activating Token Index: 251

Text #7

Max Range: 3.8208. Min Range: -3.8208

Max Act: 3.7269. Min Act: -0.1700

Data Index: 982282 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 3.8208. Min Range: -3.8208

Max Act: 3.7269. Min Act: -0.1700

Data Index: 903876 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 3.8208. Min Range: -3.8208

Max Act: 3.6956. Min Act: -0.1700

Data Index: 947702 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 3.8208. Min Range: -3.8208

Max Act: 3.6956. Min Act: -0.1700

Data Index: 1303605 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 3.8208. Min Range: -3.8208

Max Act: 3.6643. Min Act: -0.1700

Data Index: 710092 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 3.8208. Min Range: -3.8208

Max Act: 3.6643. Min Act: -0.1700

Data Index: 1182034 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 3.8208. Min Range: -3.8208

Max Act: 3.6956. Min Act: -0.1700

Data Index: 515662 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 3.8208. Min Range: -3.8208

Max Act: 3.6330. Min Act: -0.1700

Data Index: 1130908 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 3.8208. Min Range: -3.8208

Max Act: 3.6330. Min Act: -0.1700

Data Index: 723258 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 3.8208. Min Range: -3.8208

Max Act: 3.6643. Min Act: -0.1700

Data Index: 342255 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 3.8208. Min Range: -3.8208

Max Act: 3.6643. Min Act: -0.1700

Data Index: 150501 (C4 (Web Text))

Max Activating Token Index: 487

Text #18

Max Range: 3.8208. Min Range: -3.8208

Max Act: 3.6643. Min Act: -0.1700

Data Index: 294649 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 3.8208. Min Range: -3.8208

Max Act: 3.6643. Min Act: -0.1700

Data Index: 500122 (C4 (Web Text))

Max Activating Token Index: 95