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

Dataset: Open Web Text

Neuron 793 in Layer 0

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: 1.5575. Min Range: -1.5575

Max Act: 1.5575. Min Act: -0.0999

Data Index: 2133154 (Open Web Text)

Max Activating Token Index: 674

Text #1

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.5396. Min Act: -0.1033

Data Index: 7767117 (Open Web Text)

Max Activating Token Index: 868

Text #2

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.5313. Min Act: -0.1248

Data Index: 277631 (Open Web Text)

Max Activating Token Index: 351

Text #3

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.5346. Min Act: -0.0787

Data Index: 1411499 (Open Web Text)

Max Activating Token Index: 473

Text #4

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.5163. Min Act: -0.1319

Data Index: 2378555 (Open Web Text)

Max Activating Token Index: 677

Text #5

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.5135. Min Act: -0.0787

Data Index: 3720228 (Open Web Text)

Max Activating Token Index: 475

Text #6

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.5199. Min Act: -0.1389

Data Index: 3206787 (Open Web Text)

Max Activating Token Index: 662

Text #7

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.5060. Min Act: -0.0911

Data Index: 1170427 (Open Web Text)

Max Activating Token Index: 654

Text #8

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.5101. Min Act: -0.1307

Data Index: 7005323 (Open Web Text)

Max Activating Token Index: 324

Text #9

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.5124. Min Act: -0.1076

Data Index: 5777465 (Open Web Text)

Max Activating Token Index: 548

Text #10

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.5033. Min Act: -0.0787

Data Index: 8363840 (Open Web Text)

Max Activating Token Index: 428

Text #11

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.5020. Min Act: -0.1435

Data Index: 3114695 (Open Web Text)

Max Activating Token Index: 811

Text #12

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.5021. Min Act: -0.0787

Data Index: 6434512 (Open Web Text)

Max Activating Token Index: 457

Text #13

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.4931. Min Act: -0.0846

Data Index: 7371907 (Open Web Text)

Max Activating Token Index: 868

Text #14

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.4951. Min Act: -0.1633

Data Index: 475174 (Open Web Text)

Max Activating Token Index: 565

Text #15

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.4943. Min Act: -0.0936

Data Index: 3955014 (Open Web Text)

Max Activating Token Index: 685

Text #16

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.4917. Min Act: -0.1258

Data Index: 6770442 (Open Web Text)

Max Activating Token Index: 372

Text #17

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.4935. Min Act: -0.1338

Data Index: 949433 (Open Web Text)

Max Activating Token Index: 438

Text #18

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.4877. Min Act: -0.0920

Data Index: 5623692 (Open Web Text)

Max Activating Token Index: 329

Text #19

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.4921. Min Act: -0.1356

Data Index: 2679085 (Open Web Text)

Max Activating Token Index: 480