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

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

Neuron 885 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2651. Min Range: -5.2651

Max Act: 5.2651. Min Act: -0.1700

Data Index: 1321573 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 5.2651. Min Range: -5.2651

Max Act: 5.1714. Min Act: -0.1700

Data Index: 367981 (C4 (Web Text))

Max Activating Token Index: 892

Text #2

Max Range: 5.2651. Min Range: -5.2651

Max Act: 5.2339. Min Act: -0.1700

Data Index: 1236880 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 5.2651. Min Range: -5.2651

Max Act: 5.1401. Min Act: -0.1700

Data Index: 227061 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 5.2651. Min Range: -5.2651

Max Act: 5.1089. Min Act: -0.1700

Data Index: 1238132 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 5.2651. Min Range: -5.2651

Max Act: 5.1714. Min Act: -0.1700

Data Index: 1314123 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 5.2651. Min Range: -5.2651

Max Act: 5.0776. Min Act: -0.1700

Data Index: 1293641 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 5.2651. Min Range: -5.2651

Max Act: 5.0776. Min Act: -0.1700

Data Index: 791334 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 5.2651. Min Range: -5.2651

Max Act: 5.1089. Min Act: -0.1700

Data Index: 1297015 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 5.2651. Min Range: -5.2651

Max Act: 5.0776. Min Act: -0.1700

Data Index: 1253954 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 5.2651. Min Range: -5.2651

Max Act: 5.0464. Min Act: -0.1700

Data Index: 757726 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 5.2651. Min Range: -5.2651

Max Act: 5.0151. Min Act: -0.1700

Data Index: 805598 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 5.2651. Min Range: -5.2651

Max Act: 4.9839. Min Act: -0.1700

Data Index: 231787 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 5.2651. Min Range: -5.2651

Max Act: 5.0464. Min Act: -0.1700

Data Index: 391393 (C4 (Web Text))

Max Activating Token Index: 343

Text #14

Max Range: 5.2651. Min Range: -5.2651

Max Act: 4.9839. Min Act: -0.1700

Data Index: 1203303 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 5.2651. Min Range: -5.2651

Max Act: 4.9839. Min Act: -0.1700

Data Index: 493936 (C4 (Web Text))

Max Activating Token Index: 340

Text #16

Max Range: 5.2651. Min Range: -5.2651

Max Act: 4.9839. Min Act: -0.1700

Data Index: 1284082 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 5.2651. Min Range: -5.2651

Max Act: 5.0151. Min Act: -0.1700

Data Index: 1242652 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 5.2651. Min Range: -5.2651

Max Act: 4.9839. Min Act: -0.1700

Data Index: 927412 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 5.2651. Min Range: -5.2651

Max Act: 4.9526. Min Act: -0.1700

Data Index: 596556 (C4 (Web Text))

Max Activating Token Index: 981