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

Dataset: Open Web Text

Neuron 1619 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: 4.4229. Min Range: -4.4229

Max Act: 4.4229. Min Act: -0.1700

Data Index: 6252058 (Open Web Text)

Max Activating Token Index: 718

Text #1

Max Range: 4.4229. Min Range: -4.4229

Max Act: 4.0642. Min Act: -0.1700

Data Index: 5883068 (Open Web Text)

Max Activating Token Index: 63

Text #2

Max Range: 4.4229. Min Range: -4.4229

Max Act: 3.9372. Min Act: -0.1700

Data Index: 684453 (Open Web Text)

Max Activating Token Index: 725

Text #3

Max Range: 4.4229. Min Range: -4.4229

Max Act: 3.8337. Min Act: -0.1700

Data Index: 3671220 (Open Web Text)

Max Activating Token Index: 143

Text #4

Max Range: 4.4229. Min Range: -4.4229

Max Act: 3.8704. Min Act: -0.1700

Data Index: 6974133 (Open Web Text)

Max Activating Token Index: 635

Text #5

Max Range: 4.4229. Min Range: -4.4229

Max Act: 3.8606. Min Act: -0.1700

Data Index: 2090095 (Open Web Text)

Max Activating Token Index: 510

Text #6

Max Range: 4.4229. Min Range: -4.4229

Max Act: 3.8397. Min Act: -0.1700

Data Index: 8610943 (Open Web Text)

Max Activating Token Index: 172

Text #7

Max Range: 4.4229. Min Range: -4.4229

Max Act: 3.8237. Min Act: -0.1700

Data Index: 3171135 (Open Web Text)

Max Activating Token Index: 774

Text #8

Max Range: 4.4229. Min Range: -4.4229

Max Act: 3.8181. Min Act: -0.1700

Data Index: 3090318 (Open Web Text)

Max Activating Token Index: 358

Text #9

Max Range: 4.4229. Min Range: -4.4229

Max Act: 3.8463. Min Act: -0.1700

Data Index: 7673513 (Open Web Text)

Max Activating Token Index: 634

Text #10

Max Range: 4.4229. Min Range: -4.4229

Max Act: 3.8212. Min Act: -0.1700

Data Index: 6915188 (Open Web Text)

Max Activating Token Index: 687

Text #11

Max Range: 4.4229. Min Range: -4.4229

Max Act: 3.8080. Min Act: -0.1700

Data Index: 669387 (Open Web Text)

Max Activating Token Index: 100

Text #12

Max Range: 4.4229. Min Range: -4.4229

Max Act: 3.8184. Min Act: -0.1700

Data Index: 3812393 (Open Web Text)

Max Activating Token Index: 635

Text #13

Max Range: 4.4229. Min Range: -4.4229

Max Act: 3.7916. Min Act: -0.1700

Data Index: 8423242 (Open Web Text)

Max Activating Token Index: 163

Text #14

Max Range: 4.4229. Min Range: -4.4229

Max Act: 3.8019. Min Act: -0.1700

Data Index: 42759 (Open Web Text)

Max Activating Token Index: 148

Text #15

Max Range: 4.4229. Min Range: -4.4229

Max Act: 3.8024. Min Act: -0.1700

Data Index: 405164 (Open Web Text)

Max Activating Token Index: 90

Text #16

Max Range: 4.4229. Min Range: -4.4229

Max Act: 3.8138. Min Act: -0.1700

Data Index: 4646692 (Open Web Text)

Max Activating Token Index: 705

Text #17

Max Range: 4.4229. Min Range: -4.4229

Max Act: 3.8027. Min Act: -0.1700

Data Index: 7016388 (Open Web Text)

Max Activating Token Index: 682

Text #18

Max Range: 4.4229. Min Range: -4.4229

Max Act: 3.8045. Min Act: -0.1700

Data Index: 7050967 (Open Web Text)

Max Activating Token Index: 280

Text #19

Max Range: 4.4229. Min Range: -4.4229

Max Act: 3.7860. Min Act: -0.1700

Data Index: 7740370 (Open Web Text)

Max Activating Token Index: 218