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

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

Neuron 1904 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0108. Min Range: -4.0108

Max Act: 4.0108. Min Act: -0.1700

Data Index: 819266 (C4 (Web Text))

Max Activating Token Index: 226

Text #1

Max Range: 4.0108. Min Range: -4.0108

Max Act: 3.7918. Min Act: -0.1700

Data Index: 38190 (C4 (Web Text))

Max Activating Token Index: 871

Text #2

Max Range: 4.0108. Min Range: -4.0108

Max Act: 3.7762. Min Act: -0.1700

Data Index: 621146 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 4.0108. Min Range: -4.0108

Max Act: 3.7293. Min Act: -0.1700

Data Index: 1241202 (C4 (Web Text))

Max Activating Token Index: 972

Text #4

Max Range: 4.0108. Min Range: -4.0108

Max Act: 3.6823. Min Act: -0.1700

Data Index: 895583 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 4.0108. Min Range: -4.0108

Max Act: 3.6980. Min Act: -0.1700

Data Index: 925503 (C4 (Web Text))

Max Activating Token Index: 327

Text #6

Max Range: 4.0108. Min Range: -4.0108

Max Act: 3.6823. Min Act: -0.1700

Data Index: 1069317 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 4.0108. Min Range: -4.0108

Max Act: 3.6667. Min Act: -0.1700

Data Index: 1058465 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 4.0108. Min Range: -4.0108

Max Act: 3.6041. Min Act: -0.1700

Data Index: 932495 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 4.0108. Min Range: -4.0108

Max Act: 3.6354. Min Act: -0.1700

Data Index: 111827 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 4.0108. Min Range: -4.0108

Max Act: 3.6197. Min Act: -0.1700

Data Index: 824456 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 4.0108. Min Range: -4.0108

Max Act: 3.6354. Min Act: -0.1700

Data Index: 728003 (C4 (Web Text))

Max Activating Token Index: 926

Text #12

Max Range: 4.0108. Min Range: -4.0108

Max Act: 3.6197. Min Act: -0.1700

Data Index: 538585 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 4.0108. Min Range: -4.0108

Max Act: 3.6354. Min Act: -0.1700

Data Index: 929703 (C4 (Web Text))

Max Activating Token Index: 404

Text #14

Max Range: 4.0108. Min Range: -4.0108

Max Act: 3.6041. Min Act: -0.1700

Data Index: 285197 (C4 (Web Text))

Max Activating Token Index: 810

Text #15

Max Range: 4.0108. Min Range: -4.0108

Max Act: 3.5571. Min Act: -0.1700

Data Index: 785353 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 4.0108. Min Range: -4.0108

Max Act: 3.5727. Min Act: -0.1700

Data Index: 1014083 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 4.0108. Min Range: -4.0108

Max Act: 3.5884. Min Act: -0.1700

Data Index: 237041 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 4.0108. Min Range: -4.0108

Max Act: 3.5727. Min Act: -0.1700

Data Index: 821046 (C4 (Web Text))

Max Activating Token Index: 219

Text #19

Max Range: 4.0108. Min Range: -4.0108

Max Act: 3.5884. Min Act: -0.1700

Data Index: 1123985 (C4 (Web Text))

Max Activating Token Index: 886