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

Dataset: Open Web Text

Neuron 1467 in Layer 1

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: 1.3668. Min Range: -1.3668

Max Act: 1.3668. Min Act: -0.1553

Data Index: 8001133 (Open Web Text)

Max Activating Token Index: 514

Text #1

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.3513. Min Act: -0.1664

Data Index: 4040777 (Open Web Text)

Max Activating Token Index: 142

Text #2

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.3414. Min Act: -0.1652

Data Index: 8470999 (Open Web Text)

Max Activating Token Index: 254

Text #3

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.3370. Min Act: -0.1623

Data Index: 4407280 (Open Web Text)

Max Activating Token Index: 246

Text #4

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.3251. Min Act: -0.1493

Data Index: 2425396 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.3233. Min Act: -0.1498

Data Index: 6569691 (Open Web Text)

Max Activating Token Index: 333

Text #6

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.3240. Min Act: -0.1431

Data Index: 4450793 (Open Web Text)

Max Activating Token Index: 147

Text #7

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.3156. Min Act: -0.1689

Data Index: 7142790 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.3156. Min Act: -0.1305

Data Index: 3554327 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.3156. Min Act: -0.1636

Data Index: 7142800 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.3154. Min Act: -0.1448

Data Index: 6004552 (Open Web Text)

Max Activating Token Index: 31

Text #11

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.3163. Min Act: -0.1464

Data Index: 8035965 (Open Web Text)

Max Activating Token Index: 293

Text #12

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.3292. Min Act: -0.1601

Data Index: 1803453 (Open Web Text)

Max Activating Token Index: 178

Text #13

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.3340. Min Act: -0.1648

Data Index: 2348483 (Open Web Text)

Max Activating Token Index: 120

Text #14

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.3152. Min Act: -0.1679

Data Index: 464303 (Open Web Text)

Max Activating Token Index: 129

Text #15

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.3042. Min Act: -0.1514

Data Index: 4986984 (Open Web Text)

Max Activating Token Index: 439

Text #16

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.3018. Min Act: -0.1698

Data Index: 8776591 (Open Web Text)

Max Activating Token Index: 233

Text #17

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.3033. Min Act: -0.1548

Data Index: 1588559 (Open Web Text)

Max Activating Token Index: 428

Text #18

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.2986. Min Act: -0.1676

Data Index: 6634606 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.3054. Min Act: -0.1492

Data Index: 2277096 (Open Web Text)

Max Activating Token Index: 162