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

Dataset: Open Web Text

Neuron 2227 in Layer 4

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: 7.6861. Min Range: -7.6861

Max Act: 7.6172. Min Act: -0.1700

Data Index: 4178974 (Open Web Text)

Max Activating Token Index: 951

Text #1

Max Range: 7.6861. Min Range: -7.6861

Max Act: 7.6388. Min Act: -0.1700

Data Index: 3115102 (Open Web Text)

Max Activating Token Index: 933

Text #2

Max Range: 7.6861. Min Range: -7.6861

Max Act: 7.6861. Min Act: -0.1700

Data Index: 7926585 (Open Web Text)

Max Activating Token Index: 364

Text #3

Max Range: 7.6861. Min Range: -7.6861

Max Act: 7.6498. Min Act: -0.1700

Data Index: 661991 (Open Web Text)

Max Activating Token Index: 967

Text #4

Max Range: 7.6861. Min Range: -7.6861

Max Act: 7.5383. Min Act: -0.1700

Data Index: 7388698 (Open Web Text)

Max Activating Token Index: 398

Text #5

Max Range: 7.6861. Min Range: -7.6861

Max Act: 7.2823. Min Act: -0.1700

Data Index: 4162995 (Open Web Text)

Max Activating Token Index: 760

Text #6

Max Range: 7.6861. Min Range: -7.6861

Max Act: 7.2788. Min Act: -0.1700

Data Index: 7788802 (Open Web Text)

Max Activating Token Index: 509

Text #7

Max Range: 7.6861. Min Range: -7.6861

Max Act: 7.2069. Min Act: -0.1700

Data Index: 3450783 (Open Web Text)

Max Activating Token Index: 430

Text #8

Max Range: 7.6861. Min Range: -7.6861

Max Act: 7.3155. Min Act: -0.1700

Data Index: 6987804 (Open Web Text)

Max Activating Token Index: 413

Text #9

Max Range: 7.6861. Min Range: -7.6861

Max Act: 7.2239. Min Act: -0.1700

Data Index: 3779409 (Open Web Text)

Max Activating Token Index: 594

Text #10

Max Range: 7.6861. Min Range: -7.6861

Max Act: 7.2603. Min Act: -0.1700

Data Index: 2096042 (Open Web Text)

Max Activating Token Index: 735

Text #11

Max Range: 7.6861. Min Range: -7.6861

Max Act: 7.1723. Min Act: -0.1700

Data Index: 3278745 (Open Web Text)

Max Activating Token Index: 955

Text #12

Max Range: 7.6861. Min Range: -7.6861

Max Act: 7.2161. Min Act: -0.1700

Data Index: 1293574 (Open Web Text)

Max Activating Token Index: 77

Text #13

Max Range: 7.6861. Min Range: -7.6861

Max Act: 7.1785. Min Act: -0.1700

Data Index: 6462065 (Open Web Text)

Max Activating Token Index: 589

Text #14

Max Range: 7.6861. Min Range: -7.6861

Max Act: 7.1606. Min Act: -0.1700

Data Index: 4725400 (Open Web Text)

Max Activating Token Index: 334

Text #15

Max Range: 7.6861. Min Range: -7.6861

Max Act: 7.0835. Min Act: -0.1700

Data Index: 572702 (Open Web Text)

Max Activating Token Index: 607

Text #16

Max Range: 7.6861. Min Range: -7.6861

Max Act: 7.1394. Min Act: -0.1700

Data Index: 688038 (Open Web Text)

Max Activating Token Index: 147

Text #17

Max Range: 7.6861. Min Range: -7.6861

Max Act: 7.0747. Min Act: -0.1700

Data Index: 4705471 (Open Web Text)

Max Activating Token Index: 681

Text #18

Max Range: 7.6861. Min Range: -7.6861

Max Act: 7.0635. Min Act: -0.1700

Data Index: 8000277 (Open Web Text)

Max Activating Token Index: 586

Text #19

Max Range: 7.6861. Min Range: -7.6861

Max Act: 7.1211. Min Act: -0.1700

Data Index: 2096494 (Open Web Text)

Max Activating Token Index: 878