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

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

Neuron 262 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.4085. Min Act: -0.1700

Data Index: 1550342 (Python Code)

Max Activating Token Index: 475

Text #1

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.3772. Min Act: -0.1700

Data Index: 1400668 (Python Code)

Max Activating Token Index: 930

Text #2

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.3458. Min Act: -0.1700

Data Index: 1581337 (Python Code)

Max Activating Token Index: 492

Text #3

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.3144. Min Act: -0.1700

Data Index: 860250 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.2987. Min Act: -0.1700

Data Index: 595451 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.2672. Min Act: -0.1700

Data Index: 659928 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.2358. Min Act: -0.1700

Data Index: 156715 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.2515. Min Act: -0.1700

Data Index: 1321730 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.2515. Min Act: -0.1700

Data Index: 252263 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.2515. Min Act: -0.1700

Data Index: 1105708 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.2672. Min Act: -0.1700

Data Index: 958666 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.2515. Min Act: -0.1700

Data Index: 876271 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.2515. Min Act: -0.1700

Data Index: 1487563 (Python Code)

Max Activating Token Index: 962

Text #13

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.2672. Min Act: -0.1700

Data Index: 1624666 (Python Code)

Max Activating Token Index: 322

Text #14

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.2515. Min Act: -0.1700

Data Index: 224959 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.2515. Min Act: -0.1700

Data Index: 60294 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.2515. Min Act: -0.1700

Data Index: 1191912 (C4 (Web Text))

Max Activating Token Index: 684

Text #17

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.2515. Min Act: -0.1700

Data Index: 1030809 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.2515. Min Act: -0.1700

Data Index: 1274006 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.2515. Min Act: -0.1700

Data Index: 313639 (C4 (Web Text))

Max Activating Token Index: 547