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

Dataset: Open Web Text

Neuron 1752 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: 5.3403. Min Range: -5.3403

Max Act: 5.3403. Min Act: -0.1700

Data Index: 4228521 (Open Web Text)

Max Activating Token Index: 13

Text #1

Max Range: 5.3403. Min Range: -5.3403

Max Act: 5.2379. Min Act: -0.1700

Data Index: 8267663 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 5.3403. Min Range: -5.3403

Max Act: 5.2378. Min Act: -0.1700

Data Index: 7218807 (Open Web Text)

Max Activating Token Index: 12

Text #3

Max Range: 5.3403. Min Range: -5.3403

Max Act: 5.1782. Min Act: -0.1700

Data Index: 3697611 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 5.3403. Min Range: -5.3403

Max Act: 5.1345. Min Act: -0.1700

Data Index: 8256916 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 5.3403. Min Range: -5.3403

Max Act: 5.1354. Min Act: -0.1700

Data Index: 3150138 (Open Web Text)

Max Activating Token Index: 12

Text #6

Max Range: 5.3403. Min Range: -5.3403

Max Act: 5.1393. Min Act: -0.1700

Data Index: 76861 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 5.3403. Min Range: -5.3403

Max Act: 5.1112. Min Act: -0.1700

Data Index: 1372471 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 5.3403. Min Range: -5.3403

Max Act: 5.1402. Min Act: -0.1700

Data Index: 5793825 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 5.3403. Min Range: -5.3403

Max Act: 5.1227. Min Act: -0.1700

Data Index: 5474164 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 5.3403. Min Range: -5.3403

Max Act: 5.1312. Min Act: -0.1700

Data Index: 3749300 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 5.3403. Min Range: -5.3403

Max Act: 5.1072. Min Act: -0.1700

Data Index: 7049246 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 5.3403. Min Range: -5.3403

Max Act: 5.1131. Min Act: -0.1700

Data Index: 8319131 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 5.3403. Min Range: -5.3403

Max Act: 5.1304. Min Act: -0.1700

Data Index: 5985502 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 5.3403. Min Range: -5.3403

Max Act: 5.1248. Min Act: -0.1700

Data Index: 5919507 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 5.3403. Min Range: -5.3403

Max Act: 5.1108. Min Act: -0.1700

Data Index: 8011448 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 5.3403. Min Range: -5.3403

Max Act: 5.0979. Min Act: -0.1700

Data Index: 5411090 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 5.3403. Min Range: -5.3403

Max Act: 5.0775. Min Act: -0.1700

Data Index: 2650689 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 5.3403. Min Range: -5.3403

Max Act: 5.0747. Min Act: -0.1700

Data Index: 4072658 (Open Web Text)

Max Activating Token Index: 13

Text #19

Max Range: 5.3403. Min Range: -5.3403

Max Act: 5.1029. Min Act: -0.1700

Data Index: 4082346 (Open Web Text)

Max Activating Token Index: 7