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

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

Neuron 672 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: 5.6107. Min Range: -5.6107

Max Act: 5.6107. Min Act: -0.1700

Data Index: 1095041 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 5.6107. Min Range: -5.6107

Max Act: 5.5169. Min Act: -0.1700

Data Index: 571589 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 5.6107. Min Range: -5.6107

Max Act: 5.2982. Min Act: -0.1700

Data Index: 1017651 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 5.6107. Min Range: -5.6107

Max Act: 5.3919. Min Act: -0.1700

Data Index: 809825 (C4 (Web Text))

Max Activating Token Index: 519

Text #4

Max Range: 5.6107. Min Range: -5.6107

Max Act: 5.2669. Min Act: -0.1700

Data Index: 1162894 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 5.6107. Min Range: -5.6107

Max Act: 5.2982. Min Act: -0.1700

Data Index: 115276 (C4 (Web Text))

Max Activating Token Index: 542

Text #6

Max Range: 5.6107. Min Range: -5.6107

Max Act: 5.2044. Min Act: -0.1700

Data Index: 370636 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 5.6107. Min Range: -5.6107

Max Act: 5.3294. Min Act: -0.1700

Data Index: 931301 (C4 (Web Text))

Max Activating Token Index: 736

Text #8

Max Range: 5.6107. Min Range: -5.6107

Max Act: 5.1107. Min Act: -0.1700

Data Index: 1317963 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 5.6107. Min Range: -5.6107

Max Act: 5.2669. Min Act: -0.1700

Data Index: 692858 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 5.6107. Min Range: -5.6107

Max Act: 5.1419. Min Act: -0.1700

Data Index: 400791 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 5.6107. Min Range: -5.6107

Max Act: 4.9857. Min Act: -0.1700

Data Index: 445111 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 5.6107. Min Range: -5.6107

Max Act: 4.9544. Min Act: -0.1700

Data Index: 1143781 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 5.6107. Min Range: -5.6107

Max Act: 5.0794. Min Act: -0.1700

Data Index: 914611 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 5.6107. Min Range: -5.6107

Max Act: 4.9232. Min Act: -0.1700

Data Index: 515917 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 5.6107. Min Range: -5.6107

Max Act: 4.9857. Min Act: -0.1700

Data Index: 637508 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 5.6107. Min Range: -5.6107

Max Act: 4.8919. Min Act: -0.1700

Data Index: 538455 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 5.6107. Min Range: -5.6107

Max Act: 4.9232. Min Act: -0.1700

Data Index: 137713 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 5.6107. Min Range: -5.6107

Max Act: 4.8919. Min Act: -0.1700

Data Index: 1180987 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 5.6107. Min Range: -5.6107

Max Act: 4.8919. Min Act: -0.1700

Data Index: 149186 (C4 (Web Text))

Max Activating Token Index: 229