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

Dataset: Open Web Text

Neuron 915 in Layer 2

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: 4.5246. Min Range: -4.5246

Max Act: 4.5246. Min Act: -0.1700

Data Index: 2520314 (Open Web Text)

Max Activating Token Index: 223

Text #1

Max Range: 4.5246. Min Range: -4.5246

Max Act: 4.5165. Min Act: -0.1700

Data Index: 2559106 (Open Web Text)

Max Activating Token Index: 517

Text #2

Max Range: 4.5246. Min Range: -4.5246

Max Act: 4.4919. Min Act: -0.1700

Data Index: 2078889 (Open Web Text)

Max Activating Token Index: 523

Text #3

Max Range: 4.5246. Min Range: -4.5246

Max Act: 4.4801. Min Act: -0.1700

Data Index: 5173092 (Open Web Text)

Max Activating Token Index: 838

Text #4

Max Range: 4.5246. Min Range: -4.5246

Max Act: 4.4763. Min Act: -0.1700

Data Index: 2261621 (Open Web Text)

Max Activating Token Index: 415

Text #5

Max Range: 4.5246. Min Range: -4.5246

Max Act: 4.4925. Min Act: -0.1700

Data Index: 7976516 (Open Web Text)

Max Activating Token Index: 612

Text #6

Max Range: 4.5246. Min Range: -4.5246

Max Act: 4.4583. Min Act: -0.1700

Data Index: 1459645 (Open Web Text)

Max Activating Token Index: 343

Text #7

Max Range: 4.5246. Min Range: -4.5246

Max Act: 4.4251. Min Act: -0.1700

Data Index: 7696450 (Open Web Text)

Max Activating Token Index: 479

Text #8

Max Range: 4.5246. Min Range: -4.5246

Max Act: 4.4392. Min Act: -0.1700

Data Index: 5464253 (Open Web Text)

Max Activating Token Index: 495

Text #9

Max Range: 4.5246. Min Range: -4.5246

Max Act: 4.4298. Min Act: -0.1700

Data Index: 2598960 (Open Web Text)

Max Activating Token Index: 525

Text #10

Max Range: 4.5246. Min Range: -4.5246

Max Act: 4.4295. Min Act: -0.1700

Data Index: 8199092 (Open Web Text)

Max Activating Token Index: 653

Text #11

Max Range: 4.5246. Min Range: -4.5246

Max Act: 4.3925. Min Act: -0.1700

Data Index: 4604119 (Open Web Text)

Max Activating Token Index: 574

Text #12

Max Range: 4.5246. Min Range: -4.5246

Max Act: 4.4020. Min Act: -0.1700

Data Index: 1893775 (Open Web Text)

Max Activating Token Index: 754

Text #13

Max Range: 4.5246. Min Range: -4.5246

Max Act: 4.4182. Min Act: -0.1700

Data Index: 4004309 (Open Web Text)

Max Activating Token Index: 468

Text #14

Max Range: 4.5246. Min Range: -4.5246

Max Act: 4.3881. Min Act: -0.1700

Data Index: 6754398 (Open Web Text)

Max Activating Token Index: 251

Text #15

Max Range: 4.5246. Min Range: -4.5246

Max Act: 4.4140. Min Act: -0.1700

Data Index: 6168264 (Open Web Text)

Max Activating Token Index: 396

Text #16

Max Range: 4.5246. Min Range: -4.5246

Max Act: 4.3881. Min Act: -0.1700

Data Index: 5247852 (Open Web Text)

Max Activating Token Index: 464

Text #17

Max Range: 4.5246. Min Range: -4.5246

Max Act: 4.3923. Min Act: -0.1700

Data Index: 1134749 (Open Web Text)

Max Activating Token Index: 66

Text #18

Max Range: 4.5246. Min Range: -4.5246

Max Act: 4.3926. Min Act: -0.1700

Data Index: 4815974 (Open Web Text)

Max Activating Token Index: 694

Text #19

Max Range: 4.5246. Min Range: -4.5246

Max Act: 4.3925. Min Act: -0.1700

Data Index: 1406339 (Open Web Text)

Max Activating Token Index: 542