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

Dataset: Open Web Text

Neuron 3030 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: 3.4091. Min Range: -3.4091

Max Act: 3.4091. Min Act: -0.1700

Data Index: 7143733 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.4091. Min Range: -3.4091

Max Act: 3.3411. Min Act: -0.1700

Data Index: 1049329 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.4091. Min Range: -3.4091

Max Act: 3.2836. Min Act: -0.1700

Data Index: 6501142 (Open Web Text)

Max Activating Token Index: 796

Text #3

Max Range: 3.4091. Min Range: -3.4091

Max Act: 3.2822. Min Act: -0.1700

Data Index: 3545709 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.4091. Min Range: -3.4091

Max Act: 3.2627. Min Act: -0.1700

Data Index: 4188625 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.4091. Min Range: -3.4091

Max Act: 3.2695. Min Act: -0.1700

Data Index: 6786218 (Open Web Text)

Max Activating Token Index: 698

Text #6

Max Range: 3.4091. Min Range: -3.4091

Max Act: 3.2257. Min Act: -0.1700

Data Index: 3871558 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.4091. Min Range: -3.4091

Max Act: 3.2422. Min Act: -0.1700

Data Index: 8180556 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.4091. Min Range: -3.4091

Max Act: 3.2288. Min Act: -0.1700

Data Index: 2355931 (Open Web Text)

Max Activating Token Index: 18

Text #9

Max Range: 3.4091. Min Range: -3.4091

Max Act: 3.2199. Min Act: -0.1700

Data Index: 1294422 (Open Web Text)

Max Activating Token Index: 708

Text #10

Max Range: 3.4091. Min Range: -3.4091

Max Act: 3.2251. Min Act: -0.1700

Data Index: 5355785 (Open Web Text)

Max Activating Token Index: 677

Text #11

Max Range: 3.4091. Min Range: -3.4091

Max Act: 3.2132. Min Act: -0.1700

Data Index: 7089699 (Open Web Text)

Max Activating Token Index: 1002

Text #12

Max Range: 3.4091. Min Range: -3.4091

Max Act: 3.2272. Min Act: -0.1700

Data Index: 144726 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.4091. Min Range: -3.4091

Max Act: 3.2214. Min Act: -0.1700

Data Index: 8528337 (Open Web Text)

Max Activating Token Index: 439

Text #14

Max Range: 3.4091. Min Range: -3.4091

Max Act: 3.2240. Min Act: -0.1700

Data Index: 4395135 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.4091. Min Range: -3.4091

Max Act: 3.2137. Min Act: -0.1700

Data Index: 4142681 (Open Web Text)

Max Activating Token Index: 864

Text #16

Max Range: 3.4091. Min Range: -3.4091

Max Act: 3.2193. Min Act: -0.1700

Data Index: 1311389 (Open Web Text)

Max Activating Token Index: 71

Text #17

Max Range: 3.4091. Min Range: -3.4091

Max Act: 3.2104. Min Act: -0.1700

Data Index: 4443217 (Open Web Text)

Max Activating Token Index: 11

Text #18

Max Range: 3.4091. Min Range: -3.4091

Max Act: 3.2151. Min Act: -0.1700

Data Index: 2077258 (Open Web Text)

Max Activating Token Index: 685

Text #19

Max Range: 3.4091. Min Range: -3.4091

Max Act: 3.1986. Min Act: -0.1700

Data Index: 344352 (Open Web Text)

Max Activating Token Index: 6