Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1537 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.2817. Min Range: -3.2817

Max Act: 3.2817. Min Act: -0.1700

Data Index: 10074 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 3.2817. Min Range: -3.2817

Max Act: 3.2346. Min Act: -0.1700

Data Index: 1241507 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 3.2817. Min Range: -3.2817

Max Act: 3.2503. Min Act: -0.1700

Data Index: 819295 (C4 (Web Text))

Max Activating Token Index: 880

Text #3

Max Range: 3.2817. Min Range: -3.2817

Max Act: 3.2346. Min Act: -0.1700

Data Index: 556371 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 3.2817. Min Range: -3.2817

Max Act: 3.2188. Min Act: -0.1700

Data Index: 563712 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 3.2817. Min Range: -3.2817

Max Act: 3.2031. Min Act: -0.1700

Data Index: 1250491 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 3.2817. Min Range: -3.2817

Max Act: 3.2188. Min Act: -0.1700

Data Index: 890587 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 3.2817. Min Range: -3.2817

Max Act: 3.2031. Min Act: -0.1700

Data Index: 47937 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 3.2817. Min Range: -3.2817

Max Act: 3.1874. Min Act: -0.1700

Data Index: 573785 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 3.2817. Min Range: -3.2817

Max Act: 3.2188. Min Act: -0.1700

Data Index: 256119 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 3.2817. Min Range: -3.2817

Max Act: 3.1716. Min Act: -0.1700

Data Index: 879464 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 3.2817. Min Range: -3.2817

Max Act: 3.1874. Min Act: -0.1700

Data Index: 550195 (C4 (Web Text))

Max Activating Token Index: 734

Text #12

Max Range: 3.2817. Min Range: -3.2817

Max Act: 3.1402. Min Act: -0.1700

Data Index: 93502 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 3.2817. Min Range: -3.2817

Max Act: 3.1716. Min Act: -0.1700

Data Index: 69976 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 3.2817. Min Range: -3.2817

Max Act: 3.1559. Min Act: -0.1700

Data Index: 182271 (C4 (Web Text))

Max Activating Token Index: 335

Text #15

Max Range: 3.2817. Min Range: -3.2817

Max Act: 3.1716. Min Act: -0.1700

Data Index: 831690 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 3.2817. Min Range: -3.2817

Max Act: 3.1716. Min Act: -0.1700

Data Index: 996803 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 3.2817. Min Range: -3.2817

Max Act: 3.1559. Min Act: -0.1700

Data Index: 1212260 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 3.2817. Min Range: -3.2817

Max Act: 3.1402. Min Act: -0.1700

Data Index: 1097776 (C4 (Web Text))

Max Activating Token Index: 491

Text #19

Max Range: 3.2817. Min Range: -3.2817

Max Act: 3.1559. Min Act: -0.1700

Data Index: 1110767 (C4 (Web Text))

Max Activating Token Index: 302