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

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

Neuron 1285 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: 5.5566. Min Range: -5.5566

Max Act: 5.5566. Min Act: -0.1700

Data Index: 207754 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 5.5566. Min Range: -5.5566

Max Act: 5.4941. Min Act: -0.1700

Data Index: 425438 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 5.5566. Min Range: -5.5566

Max Act: 5.4628. Min Act: -0.1700

Data Index: 1025257 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 5.5566. Min Range: -5.5566

Max Act: 5.4316. Min Act: -0.1700

Data Index: 87442 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 5.5566. Min Range: -5.5566

Max Act: 5.4003. Min Act: -0.1700

Data Index: 1027466 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 5.5566. Min Range: -5.5566

Max Act: 5.3378. Min Act: -0.1700

Data Index: 1292794 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 5.5566. Min Range: -5.5566

Max Act: 5.4003. Min Act: -0.1700

Data Index: 1295978 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 5.5566. Min Range: -5.5566

Max Act: 5.2441. Min Act: -0.1700

Data Index: 409990 (C4 (Web Text))

Max Activating Token Index: 452

Text #8

Max Range: 5.5566. Min Range: -5.5566

Max Act: 5.2753. Min Act: -0.1700

Data Index: 396311 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 5.5566. Min Range: -5.5566

Max Act: 5.2441. Min Act: -0.1700

Data Index: 913799 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 5.5566. Min Range: -5.5566

Max Act: 5.2128. Min Act: -0.1700

Data Index: 589794 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 5.5566. Min Range: -5.5566

Max Act: 5.1816. Min Act: -0.1700

Data Index: 1098085 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 5.5566. Min Range: -5.5566

Max Act: 5.1816. Min Act: -0.1700

Data Index: 999580 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 5.5566. Min Range: -5.5566

Max Act: 5.1816. Min Act: -0.1700

Data Index: 601381 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 5.5566. Min Range: -5.5566

Max Act: 5.1191. Min Act: -0.1700

Data Index: 20424 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 5.5566. Min Range: -5.5566

Max Act: 5.1503. Min Act: -0.1700

Data Index: 1168103 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 5.5566. Min Range: -5.5566

Max Act: 5.2128. Min Act: -0.1700

Data Index: 376800 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 5.5566. Min Range: -5.5566

Max Act: 5.1503. Min Act: -0.1700

Data Index: 1091898 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 5.5566. Min Range: -5.5566

Max Act: 5.1191. Min Act: -0.1700

Data Index: 40700 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 5.5566. Min Range: -5.5566

Max Act: 5.0878. Min Act: -0.1700

Data Index: 750882 (C4 (Web Text))

Max Activating Token Index: 217