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

Dataset: Open Web Text

Neuron 1511 in Layer 2

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: 3.3042. Min Range: -3.3042

Max Act: 3.3042. Min Act: -0.1700

Data Index: 8285376 (Open Web Text)

Max Activating Token Index: 982

Text #1

Max Range: 3.3042. Min Range: -3.3042

Max Act: 3.2808. Min Act: -0.1700

Data Index: 924742 (Open Web Text)

Max Activating Token Index: 421

Text #2

Max Range: 3.3042. Min Range: -3.3042

Max Act: 3.2673. Min Act: -0.1700

Data Index: 4950928 (Open Web Text)

Max Activating Token Index: 228

Text #3

Max Range: 3.3042. Min Range: -3.3042

Max Act: 3.2162. Min Act: -0.1700

Data Index: 8255982 (Open Web Text)

Max Activating Token Index: 757

Text #4

Max Range: 3.3042. Min Range: -3.3042

Max Act: 3.2343. Min Act: -0.1700

Data Index: 2495486 (Open Web Text)

Max Activating Token Index: 479

Text #5

Max Range: 3.3042. Min Range: -3.3042

Max Act: 3.1776. Min Act: -0.1700

Data Index: 6605018 (Open Web Text)

Max Activating Token Index: 453

Text #6

Max Range: 3.3042. Min Range: -3.3042

Max Act: 3.1862. Min Act: -0.1700

Data Index: 6800628 (Open Web Text)

Max Activating Token Index: 811

Text #7

Max Range: 3.3042. Min Range: -3.3042

Max Act: 3.1931. Min Act: -0.1700

Data Index: 4754934 (Open Web Text)

Max Activating Token Index: 134

Text #8

Max Range: 3.3042. Min Range: -3.3042

Max Act: 3.1680. Min Act: -0.1700

Data Index: 256615 (Open Web Text)

Max Activating Token Index: 782

Text #9

Max Range: 3.3042. Min Range: -3.3042

Max Act: 3.1274. Min Act: -0.1700

Data Index: 3102782 (Open Web Text)

Max Activating Token Index: 911

Text #10

Max Range: 3.3042. Min Range: -3.3042

Max Act: 3.1246. Min Act: -0.1700

Data Index: 5484453 (Open Web Text)

Max Activating Token Index: 339

Text #11

Max Range: 3.3042. Min Range: -3.3042

Max Act: 3.1171. Min Act: -0.1700

Data Index: 2528451 (Open Web Text)

Max Activating Token Index: 362

Text #12

Max Range: 3.3042. Min Range: -3.3042

Max Act: 3.1074. Min Act: -0.1700

Data Index: 2250541 (Open Web Text)

Max Activating Token Index: 344

Text #13

Max Range: 3.3042. Min Range: -3.3042

Max Act: 3.1251. Min Act: -0.1700

Data Index: 4512540 (Open Web Text)

Max Activating Token Index: 721

Text #14

Max Range: 3.3042. Min Range: -3.3042

Max Act: 3.1293. Min Act: -0.1700

Data Index: 3045666 (Open Web Text)

Max Activating Token Index: 109

Text #15

Max Range: 3.3042. Min Range: -3.3042

Max Act: 3.1272. Min Act: -0.1700

Data Index: 4887530 (Open Web Text)

Max Activating Token Index: 110

Text #16

Max Range: 3.3042. Min Range: -3.3042

Max Act: 3.1058. Min Act: -0.1700

Data Index: 3216046 (Open Web Text)

Max Activating Token Index: 498

Text #17

Max Range: 3.3042. Min Range: -3.3042

Max Act: 3.1046. Min Act: -0.1700

Data Index: 4689646 (Open Web Text)

Max Activating Token Index: 93

Text #18

Max Range: 3.3042. Min Range: -3.3042

Max Act: 3.0846. Min Act: -0.1700

Data Index: 3746626 (Open Web Text)

Max Activating Token Index: 749

Text #19

Max Range: 3.3042. Min Range: -3.3042

Max Act: 3.1076. Min Act: -0.1700

Data Index: 6830258 (Open Web Text)

Max Activating Token Index: 944