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

Dataset: Open Web Text

Neuron 2614 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: 5.1227. Min Range: -5.1227

Max Act: 5.1227. Min Act: -0.1700

Data Index: 6206033 (Open Web Text)

Max Activating Token Index: 747

Text #1

Max Range: 5.1227. Min Range: -5.1227

Max Act: 5.0628. Min Act: -0.1700

Data Index: 8337486 (Open Web Text)

Max Activating Token Index: 280

Text #2

Max Range: 5.1227. Min Range: -5.1227

Max Act: 5.0311. Min Act: -0.1700

Data Index: 1669176 (Open Web Text)

Max Activating Token Index: 982

Text #3

Max Range: 5.1227. Min Range: -5.1227

Max Act: 4.9540. Min Act: -0.1700

Data Index: 4711726 (Open Web Text)

Max Activating Token Index: 994

Text #4

Max Range: 5.1227. Min Range: -5.1227

Max Act: 4.9093. Min Act: -0.1700

Data Index: 1589382 (Open Web Text)

Max Activating Token Index: 616

Text #5

Max Range: 5.1227. Min Range: -5.1227

Max Act: 4.9205. Min Act: -0.1700

Data Index: 1041133 (Open Web Text)

Max Activating Token Index: 975

Text #6

Max Range: 5.1227. Min Range: -5.1227

Max Act: 4.8739. Min Act: -0.1700

Data Index: 3818871 (Open Web Text)

Max Activating Token Index: 760

Text #7

Max Range: 5.1227. Min Range: -5.1227

Max Act: 4.9009. Min Act: -0.1700

Data Index: 689202 (Open Web Text)

Max Activating Token Index: 962

Text #8

Max Range: 5.1227. Min Range: -5.1227

Max Act: 4.8555. Min Act: -0.1700

Data Index: 760471 (Open Web Text)

Max Activating Token Index: 238

Text #9

Max Range: 5.1227. Min Range: -5.1227

Max Act: 4.8272. Min Act: -0.1700

Data Index: 2238312 (Open Web Text)

Max Activating Token Index: 360

Text #10

Max Range: 5.1227. Min Range: -5.1227

Max Act: 4.8076. Min Act: -0.1700

Data Index: 304566 (Open Web Text)

Max Activating Token Index: 726

Text #11

Max Range: 5.1227. Min Range: -5.1227

Max Act: 4.8380. Min Act: -0.1700

Data Index: 535464 (Open Web Text)

Max Activating Token Index: 881

Text #12

Max Range: 5.1227. Min Range: -5.1227

Max Act: 4.8008. Min Act: -0.1700

Data Index: 4306040 (Open Web Text)

Max Activating Token Index: 591

Text #13

Max Range: 5.1227. Min Range: -5.1227

Max Act: 4.7887. Min Act: -0.1700

Data Index: 4984721 (Open Web Text)

Max Activating Token Index: 719

Text #14

Max Range: 5.1227. Min Range: -5.1227

Max Act: 4.7869. Min Act: -0.1700

Data Index: 4979751 (Open Web Text)

Max Activating Token Index: 681

Text #15

Max Range: 5.1227. Min Range: -5.1227

Max Act: 4.7691. Min Act: -0.1700

Data Index: 6793394 (Open Web Text)

Max Activating Token Index: 381

Text #16

Max Range: 5.1227. Min Range: -5.1227

Max Act: 4.7281. Min Act: -0.1700

Data Index: 4472416 (Open Web Text)

Max Activating Token Index: 989

Text #17

Max Range: 5.1227. Min Range: -5.1227

Max Act: 4.7036. Min Act: -0.1700

Data Index: 5486176 (Open Web Text)

Max Activating Token Index: 639

Text #18

Max Range: 5.1227. Min Range: -5.1227

Max Act: 4.7044. Min Act: -0.1700

Data Index: 1319189 (Open Web Text)

Max Activating Token Index: 93

Text #19

Max Range: 5.1227. Min Range: -5.1227

Max Act: 4.7429. Min Act: -0.1700

Data Index: 1815915 (Open Web Text)

Max Activating Token Index: 359