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

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

Neuron 1299 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1956. Min Range: -5.1956

Max Act: 5.1956. Min Act: -0.1699

Data Index: 944662 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 5.1956. Min Range: -5.1956

Max Act: 5.1175. Min Act: -0.1700

Data Index: 950817 (C4 (Web Text))

Max Activating Token Index: 843

Text #2

Max Range: 5.1956. Min Range: -5.1956

Max Act: 5.0863. Min Act: -0.1699

Data Index: 613352 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 5.1956. Min Range: -5.1956

Max Act: 5.0863. Min Act: -0.1700

Data Index: 1140778 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 5.1956. Min Range: -5.1956

Max Act: 5.1175. Min Act: -0.1700

Data Index: 276844 (C4 (Web Text))

Max Activating Token Index: 608

Text #5

Max Range: 5.1956. Min Range: -5.1956

Max Act: 5.0081. Min Act: -0.1700

Data Index: 396059 (C4 (Web Text))

Max Activating Token Index: 954

Text #6

Max Range: 5.1956. Min Range: -5.1956

Max Act: 5.0081. Min Act: -0.1700

Data Index: 1042056 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 5.1956. Min Range: -5.1956

Max Act: 4.9925. Min Act: -0.1700

Data Index: 1173398 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 5.1956. Min Range: -5.1956

Max Act: 5.0081. Min Act: -0.1700

Data Index: 518115 (C4 (Web Text))

Max Activating Token Index: 786

Text #9

Max Range: 5.1956. Min Range: -5.1956

Max Act: 4.9769. Min Act: -0.1699

Data Index: 1093815 (C4 (Web Text))

Max Activating Token Index: 746

Text #10

Max Range: 5.1956. Min Range: -5.1956

Max Act: 4.9613. Min Act: -0.1700

Data Index: 189250 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 5.1956. Min Range: -5.1956

Max Act: 4.9769. Min Act: -0.1699

Data Index: 85062 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 5.1956. Min Range: -5.1956

Max Act: 4.9769. Min Act: -0.1700

Data Index: 1162195 (C4 (Web Text))

Max Activating Token Index: 681

Text #13

Max Range: 5.1956. Min Range: -5.1956

Max Act: 4.9613. Min Act: -0.1700

Data Index: 1339658 (C4 (Web Text))

Max Activating Token Index: 796

Text #14

Max Range: 5.1956. Min Range: -5.1956

Max Act: 4.9144. Min Act: -0.1700

Data Index: 815371 (C4 (Web Text))

Max Activating Token Index: 895

Text #15

Max Range: 5.1956. Min Range: -5.1956

Max Act: 4.8988. Min Act: -0.1700

Data Index: 1294069 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 5.1956. Min Range: -5.1956

Max Act: 4.9300. Min Act: -0.1700

Data Index: 1033678 (C4 (Web Text))

Max Activating Token Index: 472

Text #17

Max Range: 5.1956. Min Range: -5.1956

Max Act: 4.8675. Min Act: -0.1700

Data Index: 704339 (C4 (Web Text))

Max Activating Token Index: 921

Text #18

Max Range: 5.1956. Min Range: -5.1956

Max Act: 4.9144. Min Act: -0.1700

Data Index: 963440 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 5.1956. Min Range: -5.1956

Max Act: 4.9144. Min Act: -0.1700

Data Index: 506659 (C4 (Web Text))

Max Activating Token Index: 644