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

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

Neuron 74 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0990. Min Range: -5.0990

Max Act: 5.0990. Min Act: -0.1700

Data Index: 14644 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 5.0990. Min Range: -5.0990

Max Act: 5.0365. Min Act: -0.1700

Data Index: 286868 (C4 (Web Text))

Max Activating Token Index: 652

Text #2

Max Range: 5.0990. Min Range: -5.0990

Max Act: 4.9740. Min Act: -0.1700

Data Index: 797555 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 5.0990. Min Range: -5.0990

Max Act: 4.8490. Min Act: -0.1700

Data Index: 1089233 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 5.0990. Min Range: -5.0990

Max Act: 4.7865. Min Act: -0.1700

Data Index: 655733 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 5.0990. Min Range: -5.0990

Max Act: 4.8490. Min Act: -0.1700

Data Index: 375949 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 5.0990. Min Range: -5.0990

Max Act: 4.7552. Min Act: -0.1700

Data Index: 122316 (C4 (Web Text))

Max Activating Token Index: 244

Text #7

Max Range: 5.0990. Min Range: -5.0990

Max Act: 4.7552. Min Act: -0.1700

Data Index: 1183682 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 5.0990. Min Range: -5.0990

Max Act: 4.7240. Min Act: -0.1700

Data Index: 1232445 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 5.0990. Min Range: -5.0990

Max Act: 4.6927. Min Act: -0.1700

Data Index: 25969 (C4 (Web Text))

Max Activating Token Index: 281

Text #10

Max Range: 5.0990. Min Range: -5.0990

Max Act: 4.7552. Min Act: -0.1700

Data Index: 1114881 (C4 (Web Text))

Max Activating Token Index: 471

Text #11

Max Range: 5.0990. Min Range: -5.0990

Max Act: 4.6927. Min Act: -0.1700

Data Index: 874118 (C4 (Web Text))

Max Activating Token Index: 723

Text #12

Max Range: 5.0990. Min Range: -5.0990

Max Act: 4.7240. Min Act: -0.1700

Data Index: 1004288 (C4 (Web Text))

Max Activating Token Index: 454

Text #13

Max Range: 5.0990. Min Range: -5.0990

Max Act: 4.7240. Min Act: -0.1700

Data Index: 527583 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 5.0990. Min Range: -5.0990

Max Act: 4.7240. Min Act: -0.1700

Data Index: 1175893 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 5.0990. Min Range: -5.0990

Max Act: 4.7240. Min Act: -0.1700

Data Index: 829397 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 5.0990. Min Range: -5.0990

Max Act: 4.6615. Min Act: -0.1700

Data Index: 857756 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 5.0990. Min Range: -5.0990

Max Act: 4.6927. Min Act: -0.1700

Data Index: 28728 (C4 (Web Text))

Max Activating Token Index: 525

Text #18

Max Range: 5.0990. Min Range: -5.0990

Max Act: 4.6302. Min Act: -0.1700

Data Index: 770958 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 5.0990. Min Range: -5.0990

Max Act: 4.6302. Min Act: -0.1700

Data Index: 1102101 (C4 (Web Text))

Max Activating Token Index: 473