Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 605 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.8931. Min Range: -3.8931

Max Act: 3.8931. Min Act: -0.1700

Data Index: 763191 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 3.8931. Min Range: -3.8931

Max Act: 3.8775. Min Act: -0.1700

Data Index: 280123 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 3.8931. Min Range: -3.8931

Max Act: 3.8618. Min Act: -0.1700

Data Index: 716032 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 3.8931. Min Range: -3.8931

Max Act: 3.8462. Min Act: -0.1700

Data Index: 264774 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 3.8931. Min Range: -3.8931

Max Act: 3.8462. Min Act: -0.1700

Data Index: 182523 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 3.8931. Min Range: -3.8931

Max Act: 3.8305. Min Act: -0.1700

Data Index: 217266 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 3.8931. Min Range: -3.8931

Max Act: 3.8462. Min Act: -0.1700

Data Index: 1122606 (C4 (Web Text))

Max Activating Token Index: 585

Text #7

Max Range: 3.8931. Min Range: -3.8931

Max Act: 3.8462. Min Act: -0.1700

Data Index: 18329 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 3.8931. Min Range: -3.8931

Max Act: 3.8305. Min Act: -0.1700

Data Index: 854729 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 3.8931. Min Range: -3.8931

Max Act: 3.7993. Min Act: -0.1700

Data Index: 700828 (C4 (Web Text))

Max Activating Token Index: 965

Text #10

Max Range: 3.8931. Min Range: -3.8931

Max Act: 3.7993. Min Act: -0.1700

Data Index: 1169948 (C4 (Web Text))

Max Activating Token Index: 4

Text #11

Max Range: 3.8931. Min Range: -3.8931

Max Act: 3.7836. Min Act: -0.1700

Data Index: 389678 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 3.8931. Min Range: -3.8931

Max Act: 3.7836. Min Act: -0.1700

Data Index: 181742 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 3.8931. Min Range: -3.8931

Max Act: 3.7680. Min Act: -0.1700

Data Index: 865942 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 3.8931. Min Range: -3.8931

Max Act: 3.7523. Min Act: -0.1700

Data Index: 959569 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 3.8931. Min Range: -3.8931

Max Act: 3.7680. Min Act: -0.1700

Data Index: 1237256 (C4 (Web Text))

Max Activating Token Index: 514

Text #16

Max Range: 3.8931. Min Range: -3.8931

Max Act: 3.7680. Min Act: -0.1700

Data Index: 567313 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 3.8931. Min Range: -3.8931

Max Act: 3.7680. Min Act: -0.1700

Data Index: 445654 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 3.8931. Min Range: -3.8931

Max Act: 3.7680. Min Act: -0.1700

Data Index: 774636 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 3.8931. Min Range: -3.8931

Max Act: 3.7523. Min Act: -0.1700

Data Index: 783659 (C4 (Web Text))

Max Activating Token Index: 128