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

Dataset: Open Web Text

Neuron 2138 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: 4.4105. Min Range: -4.4105

Max Act: 4.4105. Min Act: -0.1700

Data Index: 7560612 (Open Web Text)

Max Activating Token Index: 441

Text #1

Max Range: 4.4105. Min Range: -4.4105

Max Act: 4.1626. Min Act: -0.1700

Data Index: 4492713 (Open Web Text)

Max Activating Token Index: 639

Text #2

Max Range: 4.4105. Min Range: -4.4105

Max Act: 4.1806. Min Act: -0.1700

Data Index: 7759261 (Open Web Text)

Max Activating Token Index: 562

Text #3

Max Range: 4.4105. Min Range: -4.4105

Max Act: 4.1971. Min Act: -0.1700

Data Index: 7741087 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.4105. Min Range: -4.4105

Max Act: 4.1719. Min Act: -0.1700

Data Index: 2875443 (Open Web Text)

Max Activating Token Index: 360

Text #5

Max Range: 4.4105. Min Range: -4.4105

Max Act: 4.1910. Min Act: -0.1700

Data Index: 830989 (Open Web Text)

Max Activating Token Index: 205

Text #6

Max Range: 4.4105. Min Range: -4.4105

Max Act: 4.2211. Min Act: -0.1700

Data Index: 3926055 (Open Web Text)

Max Activating Token Index: 343

Text #7

Max Range: 4.4105. Min Range: -4.4105

Max Act: 4.2105. Min Act: -0.1700

Data Index: 1329881 (Open Web Text)

Max Activating Token Index: 86

Text #8

Max Range: 4.4105. Min Range: -4.4105

Max Act: 4.1854. Min Act: -0.1700

Data Index: 5028944 (Open Web Text)

Max Activating Token Index: 929

Text #9

Max Range: 4.4105. Min Range: -4.4105

Max Act: 4.1705. Min Act: -0.1700

Data Index: 5937510 (Open Web Text)

Max Activating Token Index: 229

Text #10

Max Range: 4.4105. Min Range: -4.4105

Max Act: 4.1501. Min Act: -0.1700

Data Index: 5728222 (Open Web Text)

Max Activating Token Index: 927

Text #11

Max Range: 4.4105. Min Range: -4.4105

Max Act: 4.1627. Min Act: -0.1700

Data Index: 5821013 (Open Web Text)

Max Activating Token Index: 463

Text #12

Max Range: 4.4105. Min Range: -4.4105

Max Act: 4.1752. Min Act: -0.1700

Data Index: 4040896 (Open Web Text)

Max Activating Token Index: 814

Text #13

Max Range: 4.4105. Min Range: -4.4105

Max Act: 4.1632. Min Act: -0.1700

Data Index: 2378380 (Open Web Text)

Max Activating Token Index: 479

Text #14

Max Range: 4.4105. Min Range: -4.4105

Max Act: 4.1289. Min Act: -0.1700

Data Index: 2186874 (Open Web Text)

Max Activating Token Index: 466

Text #15

Max Range: 4.4105. Min Range: -4.4105

Max Act: 4.1420. Min Act: -0.1700

Data Index: 5246886 (Open Web Text)

Max Activating Token Index: 934

Text #16

Max Range: 4.4105. Min Range: -4.4105

Max Act: 4.1175. Min Act: -0.1700

Data Index: 8476066 (Open Web Text)

Max Activating Token Index: 503

Text #17

Max Range: 4.4105. Min Range: -4.4105

Max Act: 4.1377. Min Act: -0.1700

Data Index: 4625193 (Open Web Text)

Max Activating Token Index: 121

Text #18

Max Range: 4.4105. Min Range: -4.4105

Max Act: 4.1115. Min Act: -0.1700

Data Index: 4531956 (Open Web Text)

Max Activating Token Index: 642

Text #19

Max Range: 4.4105. Min Range: -4.4105

Max Act: 4.0790. Min Act: -0.1700

Data Index: 1815943 (Open Web Text)

Max Activating Token Index: 783