Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1178 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 5.6176. Min Range: -5.6176

Max Act: 5.6119. Min Act: -0.1700

Data Index: 931691 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 5.6176. Min Range: -5.6176

Max Act: 5.6176. Min Act: -0.1700

Data Index: 4288039 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 5.6176. Min Range: -5.6176

Max Act: 5.5812. Min Act: -0.1700

Data Index: 7186363 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 5.6176. Min Range: -5.6176

Max Act: 5.5492. Min Act: -0.1700

Data Index: 6844625 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 5.6176. Min Range: -5.6176

Max Act: 5.5250. Min Act: -0.1700

Data Index: 5712971 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 5.6176. Min Range: -5.6176

Max Act: 5.5182. Min Act: -0.1700

Data Index: 6878109 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 5.6176. Min Range: -5.6176

Max Act: 5.5143. Min Act: -0.1700

Data Index: 77479 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 5.6176. Min Range: -5.6176

Max Act: 5.4837. Min Act: -0.1700

Data Index: 6431675 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 5.6176. Min Range: -5.6176

Max Act: 5.4924. Min Act: -0.1700

Data Index: 2015285 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 5.6176. Min Range: -5.6176

Max Act: 5.4663. Min Act: -0.1700

Data Index: 7316657 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 5.6176. Min Range: -5.6176

Max Act: 5.4394. Min Act: -0.1700

Data Index: 7282107 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 5.6176. Min Range: -5.6176

Max Act: 5.4547. Min Act: -0.1700

Data Index: 7589015 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 5.6176. Min Range: -5.6176

Max Act: 5.4526. Min Act: -0.1700

Data Index: 5623545 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 5.6176. Min Range: -5.6176

Max Act: 5.4536. Min Act: -0.1700

Data Index: 7411253 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 5.6176. Min Range: -5.6176

Max Act: 5.4474. Min Act: -0.1700

Data Index: 797674 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 5.6176. Min Range: -5.6176

Max Act: 5.4595. Min Act: -0.1700

Data Index: 3195133 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 5.6176. Min Range: -5.6176

Max Act: 5.4494. Min Act: -0.1700

Data Index: 5455416 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 5.6176. Min Range: -5.6176

Max Act: 5.4562. Min Act: -0.1700

Data Index: 481739 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 5.6176. Min Range: -5.6176

Max Act: 5.4377. Min Act: -0.1700

Data Index: 2506566 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 5.6176. Min Range: -5.6176

Max Act: 5.4047. Min Act: -0.1700

Data Index: 3631681 (Open Web Text)

Max Activating Token Index: 6