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

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

Neuron 954 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: 4.1191. Min Range: -4.1191

Max Act: 4.1191. Min Act: -0.1700

Data Index: 459136 (C4 (Web Text))

Max Activating Token Index: 522

Text #1

Max Range: 4.1191. Min Range: -4.1191

Max Act: 4.0566. Min Act: -0.1700

Data Index: 1003901 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 4.1191. Min Range: -4.1191

Max Act: 4.0566. Min Act: -0.1700

Data Index: 902854 (C4 (Web Text))

Max Activating Token Index: 580

Text #3

Max Range: 4.1191. Min Range: -4.1191

Max Act: 3.9941. Min Act: -0.1700

Data Index: 450835 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 4.1191. Min Range: -4.1191

Max Act: 3.9628. Min Act: -0.1700

Data Index: 617154 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 4.1191. Min Range: -4.1191

Max Act: 3.9315. Min Act: -0.1700

Data Index: 128618 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 4.1191. Min Range: -4.1191

Max Act: 3.9315. Min Act: -0.1700

Data Index: 563810 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 4.1191. Min Range: -4.1191

Max Act: 3.8533. Min Act: -0.1700

Data Index: 1369801 (Python Code)

Max Activating Token Index: 419

Text #8

Max Range: 4.1191. Min Range: -4.1191

Max Act: 3.9315. Min Act: -0.1700

Data Index: 168302 (C4 (Web Text))

Max Activating Token Index: 670

Text #9

Max Range: 4.1191. Min Range: -4.1191

Max Act: 3.8064. Min Act: -0.1700

Data Index: 236140 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 4.1191. Min Range: -4.1191

Max Act: 3.8690. Min Act: -0.1700

Data Index: 672342 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 4.1191. Min Range: -4.1191

Max Act: 3.8533. Min Act: -0.1700

Data Index: 971096 (C4 (Web Text))

Max Activating Token Index: 337

Text #12

Max Range: 4.1191. Min Range: -4.1191

Max Act: 3.7908. Min Act: -0.1700

Data Index: 1596577 (Python Code)

Max Activating Token Index: 38

Text #13

Max Range: 4.1191. Min Range: -4.1191

Max Act: 3.7751. Min Act: -0.1700

Data Index: 1482672 (Python Code)

Max Activating Token Index: 39

Text #14

Max Range: 4.1191. Min Range: -4.1191

Max Act: 3.7751. Min Act: -0.1700

Data Index: 1428013 (Python Code)

Max Activating Token Index: 57

Text #15

Max Range: 4.1191. Min Range: -4.1191

Max Act: 3.7908. Min Act: -0.1700

Data Index: 560941 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 4.1191. Min Range: -4.1191

Max Act: 3.7595. Min Act: -0.1700

Data Index: 1003026 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 4.1191. Min Range: -4.1191

Max Act: 3.7126. Min Act: -0.1700

Data Index: 144917 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 4.1191. Min Range: -4.1191

Max Act: 3.7751. Min Act: -0.1700

Data Index: 1451515 (Python Code)

Max Activating Token Index: 37

Text #19

Max Range: 4.1191. Min Range: -4.1191

Max Act: 3.7126. Min Act: -0.1700

Data Index: 1206269 (C4 (Web Text))

Max Activating Token Index: 14