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

Dataset: Open Web Text

Neuron 2045 in Layer 3

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: 4.5968. Min Range: -4.5968

Max Act: 4.5968. Min Act: -0.1700

Data Index: 7938566 (Open Web Text)

Max Activating Token Index: 464

Text #1

Max Range: 4.5968. Min Range: -4.5968

Max Act: 4.5843. Min Act: -0.1700

Data Index: 2638581 (Open Web Text)

Max Activating Token Index: 996

Text #2

Max Range: 4.5968. Min Range: -4.5968

Max Act: 4.4739. Min Act: -0.1700

Data Index: 2893786 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 4.5968. Min Range: -4.5968

Max Act: 4.3681. Min Act: -0.1700

Data Index: 2424552 (Open Web Text)

Max Activating Token Index: 875

Text #4

Max Range: 4.5968. Min Range: -4.5968

Max Act: 4.4405. Min Act: -0.1700

Data Index: 6962241 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 4.5968. Min Range: -4.5968

Max Act: 4.4010. Min Act: -0.1700

Data Index: 7979757 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 4.5968. Min Range: -4.5968

Max Act: 4.3079. Min Act: -0.1700

Data Index: 8111333 (Open Web Text)

Max Activating Token Index: 656

Text #7

Max Range: 4.5968. Min Range: -4.5968

Max Act: 4.2338. Min Act: -0.1700

Data Index: 3075317 (Open Web Text)

Max Activating Token Index: 165

Text #8

Max Range: 4.5968. Min Range: -4.5968

Max Act: 4.1975. Min Act: -0.1700

Data Index: 5758354 (Open Web Text)

Max Activating Token Index: 846

Text #9

Max Range: 4.5968. Min Range: -4.5968

Max Act: 4.2008. Min Act: -0.1700

Data Index: 8536239 (Open Web Text)

Max Activating Token Index: 142

Text #10

Max Range: 4.5968. Min Range: -4.5968

Max Act: 4.2217. Min Act: -0.1700

Data Index: 2416231 (Open Web Text)

Max Activating Token Index: 549

Text #11

Max Range: 4.5968. Min Range: -4.5968

Max Act: 4.2125. Min Act: -0.1700

Data Index: 7129472 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.5968. Min Range: -4.5968

Max Act: 4.2929. Min Act: -0.1700

Data Index: 728205 (Open Web Text)

Max Activating Token Index: 789

Text #13

Max Range: 4.5968. Min Range: -4.5968

Max Act: 4.2092. Min Act: -0.1700

Data Index: 1909374 (Open Web Text)

Max Activating Token Index: 87

Text #14

Max Range: 4.5968. Min Range: -4.5968

Max Act: 4.2264. Min Act: -0.1700

Data Index: 2475204 (Open Web Text)

Max Activating Token Index: 702

Text #15

Max Range: 4.5968. Min Range: -4.5968

Max Act: 4.1108. Min Act: -0.1700

Data Index: 38458 (Open Web Text)

Max Activating Token Index: 550

Text #16

Max Range: 4.5968. Min Range: -4.5968

Max Act: 4.1648. Min Act: -0.1700

Data Index: 748208 (Open Web Text)

Max Activating Token Index: 917

Text #17

Max Range: 4.5968. Min Range: -4.5968

Max Act: 4.2174. Min Act: -0.1700

Data Index: 4216263 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 4.5968. Min Range: -4.5968

Max Act: 4.1323. Min Act: -0.1700

Data Index: 2200580 (Open Web Text)

Max Activating Token Index: 196

Text #19

Max Range: 4.5968. Min Range: -4.5968

Max Act: 4.1248. Min Act: -0.1700

Data Index: 2863224 (Open Web Text)

Max Activating Token Index: 22