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

Dataset: Open Web Text

Neuron 1147 in Layer 5

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: 5.4062. Min Range: -5.4062

Max Act: 5.4062. Min Act: -0.1700

Data Index: 387748 (Open Web Text)

Max Activating Token Index: 172

Text #1

Max Range: 5.4062. Min Range: -5.4062

Max Act: 5.3690. Min Act: -0.1700

Data Index: 1091983 (Open Web Text)

Max Activating Token Index: 765

Text #2

Max Range: 5.4062. Min Range: -5.4062

Max Act: 5.2265. Min Act: -0.1700

Data Index: 316340 (Open Web Text)

Max Activating Token Index: 224

Text #3

Max Range: 5.4062. Min Range: -5.4062

Max Act: 5.2376. Min Act: -0.1700

Data Index: 2574401 (Open Web Text)

Max Activating Token Index: 748

Text #4

Max Range: 5.4062. Min Range: -5.4062

Max Act: 5.2400. Min Act: -0.1700

Data Index: 5102903 (Open Web Text)

Max Activating Token Index: 511

Text #5

Max Range: 5.4062. Min Range: -5.4062

Max Act: 5.2129. Min Act: -0.1700

Data Index: 3260560 (Open Web Text)

Max Activating Token Index: 579

Text #6

Max Range: 5.4062. Min Range: -5.4062

Max Act: 5.1685. Min Act: -0.1700

Data Index: 2460843 (Open Web Text)

Max Activating Token Index: 28

Text #7

Max Range: 5.4062. Min Range: -5.4062

Max Act: 5.1560. Min Act: -0.1700

Data Index: 8143561 (Open Web Text)

Max Activating Token Index: 246

Text #8

Max Range: 5.4062. Min Range: -5.4062

Max Act: 5.1624. Min Act: -0.1700

Data Index: 6607439 (Open Web Text)

Max Activating Token Index: 601

Text #9

Max Range: 5.4062. Min Range: -5.4062

Max Act: 5.1852. Min Act: -0.1700

Data Index: 6182568 (Open Web Text)

Max Activating Token Index: 515

Text #10

Max Range: 5.4062. Min Range: -5.4062

Max Act: 5.1740. Min Act: -0.1700

Data Index: 3466957 (Open Web Text)

Max Activating Token Index: 219

Text #11

Max Range: 5.4062. Min Range: -5.4062

Max Act: 5.1790. Min Act: -0.1700

Data Index: 6380917 (Open Web Text)

Max Activating Token Index: 597

Text #12

Max Range: 5.4062. Min Range: -5.4062

Max Act: 5.1257. Min Act: -0.1700

Data Index: 5346886 (Open Web Text)

Max Activating Token Index: 397

Text #13

Max Range: 5.4062. Min Range: -5.4062

Max Act: 5.1562. Min Act: -0.1700

Data Index: 5298596 (Open Web Text)

Max Activating Token Index: 464

Text #14

Max Range: 5.4062. Min Range: -5.4062

Max Act: 5.1362. Min Act: -0.1700

Data Index: 6572570 (Open Web Text)

Max Activating Token Index: 774

Text #15

Max Range: 5.4062. Min Range: -5.4062

Max Act: 5.1302. Min Act: -0.1700

Data Index: 2654059 (Open Web Text)

Max Activating Token Index: 250

Text #16

Max Range: 5.4062. Min Range: -5.4062

Max Act: 5.0651. Min Act: -0.1700

Data Index: 8645558 (Open Web Text)

Max Activating Token Index: 293

Text #17

Max Range: 5.4062. Min Range: -5.4062

Max Act: 5.0934. Min Act: -0.1700

Data Index: 3242141 (Open Web Text)

Max Activating Token Index: 143

Text #18

Max Range: 5.4062. Min Range: -5.4062

Max Act: 5.1026. Min Act: -0.1700

Data Index: 4604232 (Open Web Text)

Max Activating Token Index: 151

Text #19

Max Range: 5.4062. Min Range: -5.4062

Max Act: 5.0416. Min Act: -0.1700

Data Index: 7764494 (Open Web Text)

Max Activating Token Index: 647