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

Dataset: Open Web Text

Neuron 1390 in Layer 6

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: 5.0034. Min Range: -5.0034

Max Act: 5.0034. Min Act: -0.1700

Data Index: 3435252 (Open Web Text)

Max Activating Token Index: 398

Text #1

Max Range: 5.0034. Min Range: -5.0034

Max Act: 4.8329. Min Act: -0.1700

Data Index: 6297105 (Open Web Text)

Max Activating Token Index: 727

Text #2

Max Range: 5.0034. Min Range: -5.0034

Max Act: 4.7592. Min Act: -0.1700

Data Index: 4861330 (Open Web Text)

Max Activating Token Index: 583

Text #3

Max Range: 5.0034. Min Range: -5.0034

Max Act: 4.7507. Min Act: -0.1700

Data Index: 1515186 (Open Web Text)

Max Activating Token Index: 417

Text #4

Max Range: 5.0034. Min Range: -5.0034

Max Act: 4.7043. Min Act: -0.1700

Data Index: 4820062 (Open Web Text)

Max Activating Token Index: 283

Text #5

Max Range: 5.0034. Min Range: -5.0034

Max Act: 4.7086. Min Act: -0.1700

Data Index: 8395399 (Open Web Text)

Max Activating Token Index: 489

Text #6

Max Range: 5.0034. Min Range: -5.0034

Max Act: 4.6719. Min Act: -0.1700

Data Index: 6717010 (Open Web Text)

Max Activating Token Index: 314

Text #7

Max Range: 5.0034. Min Range: -5.0034

Max Act: 4.6901. Min Act: -0.1700

Data Index: 4786461 (Open Web Text)

Max Activating Token Index: 960

Text #8

Max Range: 5.0034. Min Range: -5.0034

Max Act: 4.6135. Min Act: -0.1700

Data Index: 5842044 (Open Web Text)

Max Activating Token Index: 455

Text #9

Max Range: 5.0034. Min Range: -5.0034

Max Act: 4.6451. Min Act: -0.1700

Data Index: 8357606 (Open Web Text)

Max Activating Token Index: 77

Text #10

Max Range: 5.0034. Min Range: -5.0034

Max Act: 4.6397. Min Act: -0.1700

Data Index: 8350517 (Open Web Text)

Max Activating Token Index: 132

Text #11

Max Range: 5.0034. Min Range: -5.0034

Max Act: 4.6095. Min Act: -0.1700

Data Index: 4653601 (Open Web Text)

Max Activating Token Index: 350

Text #12

Max Range: 5.0034. Min Range: -5.0034

Max Act: 4.5427. Min Act: -0.1700

Data Index: 1361764 (Open Web Text)

Max Activating Token Index: 964

Text #13

Max Range: 5.0034. Min Range: -5.0034

Max Act: 4.5769. Min Act: -0.1700

Data Index: 8294067 (Open Web Text)

Max Activating Token Index: 242

Text #14

Max Range: 5.0034. Min Range: -5.0034

Max Act: 4.5934. Min Act: -0.1700

Data Index: 7903373 (Open Web Text)

Max Activating Token Index: 396

Text #15

Max Range: 5.0034. Min Range: -5.0034

Max Act: 4.5844. Min Act: -0.1700

Data Index: 6902970 (Open Web Text)

Max Activating Token Index: 680

Text #16

Max Range: 5.0034. Min Range: -5.0034

Max Act: 4.4943. Min Act: -0.1700

Data Index: 1470025 (Open Web Text)

Max Activating Token Index: 495

Text #17

Max Range: 5.0034. Min Range: -5.0034

Max Act: 4.5336. Min Act: -0.1700

Data Index: 5720359 (Open Web Text)

Max Activating Token Index: 796

Text #18

Max Range: 5.0034. Min Range: -5.0034

Max Act: 4.5235. Min Act: -0.1700

Data Index: 3563143 (Open Web Text)

Max Activating Token Index: 848

Text #19

Max Range: 5.0034. Min Range: -5.0034

Max Act: 4.5252. Min Act: -0.1700

Data Index: 2410158 (Open Web Text)

Max Activating Token Index: 239