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

Dataset: Open Web Text

Neuron 2605 in Layer 6

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: 3.4398. Min Range: -3.4398

Max Act: 3.4398. Min Act: -0.1700

Data Index: 2954047 (Open Web Text)

Max Activating Token Index: 882

Text #1

Max Range: 3.4398. Min Range: -3.4398

Max Act: 3.4119. Min Act: -0.1700

Data Index: 7094314 (Open Web Text)

Max Activating Token Index: 99

Text #2

Max Range: 3.4398. Min Range: -3.4398

Max Act: 3.3924. Min Act: -0.1700

Data Index: 3099983 (Open Web Text)

Max Activating Token Index: 896

Text #3

Max Range: 3.4398. Min Range: -3.4398

Max Act: 3.3538. Min Act: -0.1700

Data Index: 7455652 (Open Web Text)

Max Activating Token Index: 1000

Text #4

Max Range: 3.4398. Min Range: -3.4398

Max Act: 3.3492. Min Act: -0.1700

Data Index: 1646868 (Open Web Text)

Max Activating Token Index: 600

Text #5

Max Range: 3.4398. Min Range: -3.4398

Max Act: 3.3269. Min Act: -0.1700

Data Index: 632206 (Open Web Text)

Max Activating Token Index: 1018

Text #6

Max Range: 3.4398. Min Range: -3.4398

Max Act: 3.3139. Min Act: -0.1700

Data Index: 7023283 (Open Web Text)

Max Activating Token Index: 1005

Text #7

Max Range: 3.4398. Min Range: -3.4398

Max Act: 3.3215. Min Act: -0.1700

Data Index: 4240493 (Open Web Text)

Max Activating Token Index: 998

Text #8

Max Range: 3.4398. Min Range: -3.4398

Max Act: 3.3222. Min Act: -0.1700

Data Index: 685856 (Open Web Text)

Max Activating Token Index: 719

Text #9

Max Range: 3.4398. Min Range: -3.4398

Max Act: 3.3216. Min Act: -0.1700

Data Index: 5058249 (Open Web Text)

Max Activating Token Index: 661

Text #10

Max Range: 3.4398. Min Range: -3.4398

Max Act: 3.2920. Min Act: -0.1700

Data Index: 5116079 (Open Web Text)

Max Activating Token Index: 673

Text #11

Max Range: 3.4398. Min Range: -3.4398

Max Act: 3.2820. Min Act: -0.1700

Data Index: 2710265 (Open Web Text)

Max Activating Token Index: 716

Text #12

Max Range: 3.4398. Min Range: -3.4398

Max Act: 3.2772. Min Act: -0.1700

Data Index: 7547114 (Open Web Text)

Max Activating Token Index: 792

Text #13

Max Range: 3.4398. Min Range: -3.4398

Max Act: 3.2582. Min Act: -0.1700

Data Index: 98038 (Open Web Text)

Max Activating Token Index: 298

Text #14

Max Range: 3.4398. Min Range: -3.4398

Max Act: 3.2679. Min Act: -0.1700

Data Index: 7304639 (Open Web Text)

Max Activating Token Index: 899

Text #15

Max Range: 3.4398. Min Range: -3.4398

Max Act: 3.2568. Min Act: -0.1700

Data Index: 8500944 (Open Web Text)

Max Activating Token Index: 368

Text #16

Max Range: 3.4398. Min Range: -3.4398

Max Act: 3.2499. Min Act: -0.1700

Data Index: 1916967 (Open Web Text)

Max Activating Token Index: 178

Text #17

Max Range: 3.4398. Min Range: -3.4398

Max Act: 3.2563. Min Act: -0.1700

Data Index: 3907060 (Open Web Text)

Max Activating Token Index: 129

Text #18

Max Range: 3.4398. Min Range: -3.4398

Max Act: 3.2455. Min Act: -0.1700

Data Index: 2861215 (Open Web Text)

Max Activating Token Index: 392

Text #19

Max Range: 3.4398. Min Range: -3.4398

Max Act: 3.2398. Min Act: -0.1700

Data Index: 6085008 (Open Web Text)

Max Activating Token Index: 73