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

Dataset: Open Web Text

Neuron 2974 in Layer 1

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: 3.0432. Min Range: -3.0432

Max Act: 3.0432. Min Act: -0.1700

Data Index: 6395067 (Open Web Text)

Max Activating Token Index: 206

Text #1

Max Range: 3.0432. Min Range: -3.0432

Max Act: 3.0166. Min Act: -0.1700

Data Index: 6893623 (Open Web Text)

Max Activating Token Index: 268

Text #2

Max Range: 3.0432. Min Range: -3.0432

Max Act: 2.9687. Min Act: -0.1700

Data Index: 6664174 (Open Web Text)

Max Activating Token Index: 840

Text #3

Max Range: 3.0432. Min Range: -3.0432

Max Act: 2.7643. Min Act: -0.1700

Data Index: 5862353 (Open Web Text)

Max Activating Token Index: 776

Text #4

Max Range: 3.0432. Min Range: -3.0432

Max Act: 2.7634. Min Act: -0.1700

Data Index: 6955853 (Open Web Text)

Max Activating Token Index: 655

Text #5

Max Range: 3.0432. Min Range: -3.0432

Max Act: 2.7156. Min Act: -0.1700

Data Index: 2421728 (Open Web Text)

Max Activating Token Index: 952

Text #6

Max Range: 3.0432. Min Range: -3.0432

Max Act: 2.7013. Min Act: -0.1700

Data Index: 7710973 (Open Web Text)

Max Activating Token Index: 314

Text #7

Max Range: 3.0432. Min Range: -3.0432

Max Act: 2.6986. Min Act: -0.1700

Data Index: 5600164 (Open Web Text)

Max Activating Token Index: 286

Text #8

Max Range: 3.0432. Min Range: -3.0432

Max Act: 2.6594. Min Act: -0.1700

Data Index: 7241904 (Open Web Text)

Max Activating Token Index: 500

Text #9

Max Range: 3.0432. Min Range: -3.0432

Max Act: 2.6233. Min Act: -0.1700

Data Index: 5466292 (Open Web Text)

Max Activating Token Index: 916

Text #10

Max Range: 3.0432. Min Range: -3.0432

Max Act: 2.6344. Min Act: -0.1700

Data Index: 4231725 (Open Web Text)

Max Activating Token Index: 431

Text #11

Max Range: 3.0432. Min Range: -3.0432

Max Act: 2.6138. Min Act: -0.1700

Data Index: 7929552 (Open Web Text)

Max Activating Token Index: 946

Text #12

Max Range: 3.0432. Min Range: -3.0432

Max Act: 2.5668. Min Act: -0.1700

Data Index: 6895048 (Open Web Text)

Max Activating Token Index: 746

Text #13

Max Range: 3.0432. Min Range: -3.0432

Max Act: 2.5267. Min Act: -0.1700

Data Index: 2997644 (Open Web Text)

Max Activating Token Index: 628

Text #14

Max Range: 3.0432. Min Range: -3.0432

Max Act: 2.4911. Min Act: -0.1699

Data Index: 4881656 (Open Web Text)

Max Activating Token Index: 759

Text #15

Max Range: 3.0432. Min Range: -3.0432

Max Act: 2.4950. Min Act: -0.1700

Data Index: 4938772 (Open Web Text)

Max Activating Token Index: 507

Text #16

Max Range: 3.0432. Min Range: -3.0432

Max Act: 2.4569. Min Act: -0.1700

Data Index: 2486416 (Open Web Text)

Max Activating Token Index: 853

Text #17

Max Range: 3.0432. Min Range: -3.0432

Max Act: 2.4681. Min Act: -0.1700

Data Index: 1809332 (Open Web Text)

Max Activating Token Index: 672

Text #18

Max Range: 3.0432. Min Range: -3.0432

Max Act: 2.4311. Min Act: -0.1700

Data Index: 7750190 (Open Web Text)

Max Activating Token Index: 238

Text #19

Max Range: 3.0432. Min Range: -3.0432

Max Act: 2.3848. Min Act: -0.1700

Data Index: 7305787 (Open Web Text)

Max Activating Token Index: 533