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

Dataset: Open Web Text

Neuron 2952 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: 1.6973. Min Range: -1.6973

Max Act: 1.6973. Min Act: -0.0260

Data Index: 8292927 (Open Web Text)

Max Activating Token Index: 860

Text #1

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.6853. Min Act: -0.0260

Data Index: 7520127 (Open Web Text)

Max Activating Token Index: 856

Text #2

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.6705. Min Act: -0.0260

Data Index: 6425961 (Open Web Text)

Max Activating Token Index: 601

Text #3

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.6699. Min Act: -0.0260

Data Index: 4798385 (Open Web Text)

Max Activating Token Index: 110

Text #4

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.6602. Min Act: -0.0260

Data Index: 3105882 (Open Web Text)

Max Activating Token Index: 895

Text #5

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.6508. Min Act: -0.0260

Data Index: 7199763 (Open Web Text)

Max Activating Token Index: 511

Text #6

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.6508. Min Act: -0.0260

Data Index: 3595785 (Open Web Text)

Max Activating Token Index: 819

Text #7

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.6431. Min Act: -0.0260

Data Index: 4382184 (Open Web Text)

Max Activating Token Index: 669

Text #8

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.6401. Min Act: -0.0260

Data Index: 4030874 (Open Web Text)

Max Activating Token Index: 576

Text #9

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.6403. Min Act: -0.0260

Data Index: 8017856 (Open Web Text)

Max Activating Token Index: 352

Text #10

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.6428. Min Act: -0.0439

Data Index: 6862833 (Open Web Text)

Max Activating Token Index: 648

Text #11

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.6363. Min Act: -0.0260

Data Index: 6276291 (Open Web Text)

Max Activating Token Index: 874

Text #12

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.6387. Min Act: -0.0260

Data Index: 33484 (Open Web Text)

Max Activating Token Index: 138

Text #13

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.6332. Min Act: -0.0322

Data Index: 6502480 (Open Web Text)

Max Activating Token Index: 501

Text #14

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.6319. Min Act: -0.0659

Data Index: 2129948 (Open Web Text)

Max Activating Token Index: 222

Text #15

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.6303. Min Act: -0.0567

Data Index: 2581054 (Open Web Text)

Max Activating Token Index: 616

Text #16

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.6292. Min Act: -0.0260

Data Index: 4071231 (Open Web Text)

Max Activating Token Index: 406

Text #17

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.6240. Min Act: -0.0644

Data Index: 5358590 (Open Web Text)

Max Activating Token Index: 132

Text #18

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.6303. Min Act: -0.0260

Data Index: 2986142 (Open Web Text)

Max Activating Token Index: 369

Text #19

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.6214. Min Act: -0.0260

Data Index: 2766951 (Open Web Text)

Max Activating Token Index: 309