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

Dataset: Open Web Text

Neuron 1619 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: 3.9456. Min Range: -3.9456

Max Act: 3.9456. Min Act: -0.1700

Data Index: 4460683 (Open Web Text)

Max Activating Token Index: 829

Text #1

Max Range: 3.9456. Min Range: -3.9456

Max Act: 3.9283. Min Act: -0.1700

Data Index: 1319337 (Open Web Text)

Max Activating Token Index: 674

Text #2

Max Range: 3.9456. Min Range: -3.9456

Max Act: 3.9385. Min Act: -0.1699

Data Index: 7162683 (Open Web Text)

Max Activating Token Index: 538

Text #3

Max Range: 3.9456. Min Range: -3.9456

Max Act: 3.9092. Min Act: -0.1700

Data Index: 949517 (Open Web Text)

Max Activating Token Index: 544

Text #4

Max Range: 3.9456. Min Range: -3.9456

Max Act: 3.9189. Min Act: -0.1700

Data Index: 2074460 (Open Web Text)

Max Activating Token Index: 369

Text #5

Max Range: 3.9456. Min Range: -3.9456

Max Act: 3.9173. Min Act: -0.1700

Data Index: 5797449 (Open Web Text)

Max Activating Token Index: 843

Text #6

Max Range: 3.9456. Min Range: -3.9456

Max Act: 3.9161. Min Act: -0.1700

Data Index: 3357027 (Open Web Text)

Max Activating Token Index: 710

Text #7

Max Range: 3.9456. Min Range: -3.9456

Max Act: 3.8971. Min Act: -0.1700

Data Index: 2390400 (Open Web Text)

Max Activating Token Index: 483

Text #8

Max Range: 3.9456. Min Range: -3.9456

Max Act: 3.9108. Min Act: -0.1700

Data Index: 5879787 (Open Web Text)

Max Activating Token Index: 545

Text #9

Max Range: 3.9456. Min Range: -3.9456

Max Act: 3.8544. Min Act: -0.1700

Data Index: 7457027 (Open Web Text)

Max Activating Token Index: 877

Text #10

Max Range: 3.9456. Min Range: -3.9456

Max Act: 3.8894. Min Act: -0.1700

Data Index: 7141704 (Open Web Text)

Max Activating Token Index: 541

Text #11

Max Range: 3.9456. Min Range: -3.9456

Max Act: 3.8775. Min Act: -0.1700

Data Index: 6472746 (Open Web Text)

Max Activating Token Index: 608

Text #12

Max Range: 3.9456. Min Range: -3.9456

Max Act: 3.8883. Min Act: -0.1700

Data Index: 6444243 (Open Web Text)

Max Activating Token Index: 546

Text #13

Max Range: 3.9456. Min Range: -3.9456

Max Act: 3.8836. Min Act: -0.1700

Data Index: 6195120 (Open Web Text)

Max Activating Token Index: 559

Text #14

Max Range: 3.9456. Min Range: -3.9456

Max Act: 3.8962. Min Act: -0.1700

Data Index: 5712955 (Open Web Text)

Max Activating Token Index: 423

Text #15

Max Range: 3.9456. Min Range: -3.9456

Max Act: 3.9076. Min Act: -0.1700

Data Index: 4977005 (Open Web Text)

Max Activating Token Index: 254

Text #16

Max Range: 3.9456. Min Range: -3.9456

Max Act: 3.8735. Min Act: -0.1700

Data Index: 3945043 (Open Web Text)

Max Activating Token Index: 506

Text #17

Max Range: 3.9456. Min Range: -3.9456

Max Act: 3.8869. Min Act: -0.1700

Data Index: 92690 (Open Web Text)

Max Activating Token Index: 875

Text #18

Max Range: 3.9456. Min Range: -3.9456

Max Act: 3.8928. Min Act: -0.1700

Data Index: 3897051 (Open Web Text)

Max Activating Token Index: 493

Text #19

Max Range: 3.9456. Min Range: -3.9456

Max Act: 3.8880. Min Act: -0.1700

Data Index: 1664050 (Open Web Text)

Max Activating Token Index: 627