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

Dataset: Open Web Text

Neuron 846 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: 3.0703. Min Range: -3.0703

Max Act: 3.0703. Min Act: -0.1700

Data Index: 7107569 (Open Web Text)

Max Activating Token Index: 457

Text #1

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.9798. Min Act: -0.1700

Data Index: 4460925 (Open Web Text)

Max Activating Token Index: 181

Text #2

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.9891. Min Act: -0.1700

Data Index: 7263923 (Open Web Text)

Max Activating Token Index: 865

Text #3

Max Range: 3.0703. Min Range: -3.0703

Max Act: 3.0001. Min Act: -0.1700

Data Index: 1387724 (Open Web Text)

Max Activating Token Index: 245

Text #4

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.9713. Min Act: -0.1700

Data Index: 7716018 (Open Web Text)

Max Activating Token Index: 302

Text #5

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.9738. Min Act: -0.1700

Data Index: 5825675 (Open Web Text)

Max Activating Token Index: 920

Text #6

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.9501. Min Act: -0.1700

Data Index: 6487602 (Open Web Text)

Max Activating Token Index: 374

Text #7

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.9604. Min Act: -0.1700

Data Index: 8035452 (Open Web Text)

Max Activating Token Index: 757

Text #8

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.9428. Min Act: -0.1700

Data Index: 6503545 (Open Web Text)

Max Activating Token Index: 358

Text #9

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.9543. Min Act: -0.1700

Data Index: 6954524 (Open Web Text)

Max Activating Token Index: 797

Text #10

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.9042. Min Act: -0.1700

Data Index: 117194 (Open Web Text)

Max Activating Token Index: 72

Text #11

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.9293. Min Act: -0.1700

Data Index: 1965693 (Open Web Text)

Max Activating Token Index: 940

Text #12

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.9152. Min Act: -0.1700

Data Index: 4068607 (Open Web Text)

Max Activating Token Index: 774

Text #13

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.9243. Min Act: -0.1700

Data Index: 1971085 (Open Web Text)

Max Activating Token Index: 142

Text #14

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.9022. Min Act: -0.1700

Data Index: 8476605 (Open Web Text)

Max Activating Token Index: 506

Text #15

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.9120. Min Act: -0.1700

Data Index: 2407130 (Open Web Text)

Max Activating Token Index: 264

Text #16

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.9268. Min Act: -0.1700

Data Index: 8543316 (Open Web Text)

Max Activating Token Index: 502

Text #17

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.9134. Min Act: -0.1700

Data Index: 4060908 (Open Web Text)

Max Activating Token Index: 154

Text #18

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.9266. Min Act: -0.1700

Data Index: 6827508 (Open Web Text)

Max Activating Token Index: 173

Text #19

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.8966. Min Act: -0.1700

Data Index: 7545896 (Open Web Text)

Max Activating Token Index: 339