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

Dataset: Open Web Text

Neuron 1378 in Layer 4

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: 0.8503. Min Range: -0.8503

Max Act: 0.8503. Min Act: -0.1700

Data Index: 4996137 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.8363. Min Act: -0.1700

Data Index: 4730654 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.8444. Min Act: -0.1700

Data Index: 2693242 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.8191. Min Act: -0.1700

Data Index: 4060070 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.8243. Min Act: -0.1700

Data Index: 3876874 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.8214. Min Act: -0.1700

Data Index: 1592434 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.8304. Min Act: -0.1700

Data Index: 7127702 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.8200. Min Act: -0.1700

Data Index: 5970411 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.8182. Min Act: -0.1700

Data Index: 1070752 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.8138. Min Act: -0.1700

Data Index: 8662119 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.8139. Min Act: -0.1700

Data Index: 1628605 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.8149. Min Act: -0.1700

Data Index: 1814741 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.8148. Min Act: -0.1700

Data Index: 5321026 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.8172. Min Act: -0.1700

Data Index: 609692 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.8095. Min Act: -0.1700

Data Index: 2784208 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.8063. Min Act: -0.1700

Data Index: 3056713 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.8100. Min Act: -0.1700

Data Index: 1565112 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.8095. Min Act: -0.1700

Data Index: 3081428 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.8095. Min Act: -0.1700

Data Index: 3776185 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.7981. Min Act: -0.1700

Data Index: 1686565 (Open Web Text)

Max Activating Token Index: 4