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

Dataset: Open Web Text

Neuron 2966 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: 3.0701. Min Range: -3.0701

Max Act: 3.0622. Min Act: -0.1700

Data Index: 4032086 (Open Web Text)

Max Activating Token Index: 61

Text #1

Max Range: 3.0701. Min Range: -3.0701

Max Act: 3.0701. Min Act: -0.1700

Data Index: 3144212 (Open Web Text)

Max Activating Token Index: 432

Text #2

Max Range: 3.0701. Min Range: -3.0701

Max Act: 2.9940. Min Act: -0.1700

Data Index: 6445775 (Open Web Text)

Max Activating Token Index: 561

Text #3

Max Range: 3.0701. Min Range: -3.0701

Max Act: 2.9342. Min Act: -0.1700

Data Index: 6588510 (Open Web Text)

Max Activating Token Index: 662

Text #4

Max Range: 3.0701. Min Range: -3.0701

Max Act: 2.8890. Min Act: -0.1700

Data Index: 1720846 (Open Web Text)

Max Activating Token Index: 689

Text #5

Max Range: 3.0701. Min Range: -3.0701

Max Act: 2.8917. Min Act: -0.1700

Data Index: 900913 (Open Web Text)

Max Activating Token Index: 466

Text #6

Max Range: 3.0701. Min Range: -3.0701

Max Act: 2.8960. Min Act: -0.1700

Data Index: 246449 (Open Web Text)

Max Activating Token Index: 740

Text #7

Max Range: 3.0701. Min Range: -3.0701

Max Act: 2.8957. Min Act: -0.1700

Data Index: 8015962 (Open Web Text)

Max Activating Token Index: 856

Text #8

Max Range: 3.0701. Min Range: -3.0701

Max Act: 2.8988. Min Act: -0.1700

Data Index: 7032395 (Open Web Text)

Max Activating Token Index: 951

Text #9

Max Range: 3.0701. Min Range: -3.0701

Max Act: 2.8399. Min Act: -0.1700

Data Index: 2981921 (Open Web Text)

Max Activating Token Index: 460

Text #10

Max Range: 3.0701. Min Range: -3.0701

Max Act: 2.8407. Min Act: -0.1700

Data Index: 5079749 (Open Web Text)

Max Activating Token Index: 529

Text #11

Max Range: 3.0701. Min Range: -3.0701

Max Act: 2.8434. Min Act: -0.1700

Data Index: 4271049 (Open Web Text)

Max Activating Token Index: 363

Text #12

Max Range: 3.0701. Min Range: -3.0701

Max Act: 2.8414. Min Act: -0.1700

Data Index: 2193926 (Open Web Text)

Max Activating Token Index: 693

Text #13

Max Range: 3.0701. Min Range: -3.0701

Max Act: 2.8394. Min Act: -0.1700

Data Index: 8179469 (Open Web Text)

Max Activating Token Index: 520

Text #14

Max Range: 3.0701. Min Range: -3.0701

Max Act: 2.8291. Min Act: -0.1700

Data Index: 3724845 (Open Web Text)

Max Activating Token Index: 862

Text #15

Max Range: 3.0701. Min Range: -3.0701

Max Act: 2.8002. Min Act: -0.1700

Data Index: 6819198 (Open Web Text)

Max Activating Token Index: 654

Text #16

Max Range: 3.0701. Min Range: -3.0701

Max Act: 2.8166. Min Act: -0.1700

Data Index: 5621584 (Open Web Text)

Max Activating Token Index: 936

Text #17

Max Range: 3.0701. Min Range: -3.0701

Max Act: 2.8255. Min Act: -0.1700

Data Index: 1194452 (Open Web Text)

Max Activating Token Index: 238

Text #18

Max Range: 3.0701. Min Range: -3.0701

Max Act: 2.8221. Min Act: -0.1700

Data Index: 5758567 (Open Web Text)

Max Activating Token Index: 939

Text #19

Max Range: 3.0701. Min Range: -3.0701

Max Act: 2.8165. Min Act: -0.1700

Data Index: 2480192 (Open Web Text)

Max Activating Token Index: 736