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

Dataset: Open Web Text

Neuron 1217 in Layer 4

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: 2.8049. Min Range: -2.8049

Max Act: 2.7990. Min Act: -0.1700

Data Index: 3438881 (Open Web Text)

Max Activating Token Index: 542

Text #1

Max Range: 2.8049. Min Range: -2.8049

Max Act: 2.8049. Min Act: -0.1700

Data Index: 7606593 (Open Web Text)

Max Activating Token Index: 258

Text #2

Max Range: 2.8049. Min Range: -2.8049

Max Act: 2.7855. Min Act: -0.1700

Data Index: 5214534 (Open Web Text)

Max Activating Token Index: 213

Text #3

Max Range: 2.8049. Min Range: -2.8049

Max Act: 2.7643. Min Act: -0.1700

Data Index: 5040054 (Open Web Text)

Max Activating Token Index: 284

Text #4

Max Range: 2.8049. Min Range: -2.8049

Max Act: 2.7534. Min Act: -0.1700

Data Index: 487352 (Open Web Text)

Max Activating Token Index: 434

Text #5

Max Range: 2.8049. Min Range: -2.8049

Max Act: 2.7622. Min Act: -0.1700

Data Index: 1961917 (Open Web Text)

Max Activating Token Index: 166

Text #6

Max Range: 2.8049. Min Range: -2.8049

Max Act: 2.7459. Min Act: -0.1700

Data Index: 3696547 (Open Web Text)

Max Activating Token Index: 280

Text #7

Max Range: 2.8049. Min Range: -2.8049

Max Act: 2.7117. Min Act: -0.1700

Data Index: 3006111 (Open Web Text)

Max Activating Token Index: 452

Text #8

Max Range: 2.8049. Min Range: -2.8049

Max Act: 2.7348. Min Act: -0.1700

Data Index: 851682 (Open Web Text)

Max Activating Token Index: 465

Text #9

Max Range: 2.8049. Min Range: -2.8049

Max Act: 2.6968. Min Act: -0.1700

Data Index: 7548358 (Open Web Text)

Max Activating Token Index: 489

Text #10

Max Range: 2.8049. Min Range: -2.8049

Max Act: 2.7076. Min Act: -0.1700

Data Index: 3178564 (Open Web Text)

Max Activating Token Index: 550

Text #11

Max Range: 2.8049. Min Range: -2.8049

Max Act: 2.7014. Min Act: -0.1700

Data Index: 6331464 (Open Web Text)

Max Activating Token Index: 493

Text #12

Max Range: 2.8049. Min Range: -2.8049

Max Act: 2.7029. Min Act: -0.1700

Data Index: 205919 (Open Web Text)

Max Activating Token Index: 395

Text #13

Max Range: 2.8049. Min Range: -2.8049

Max Act: 2.6585. Min Act: -0.1700

Data Index: 4383979 (Open Web Text)

Max Activating Token Index: 835

Text #14

Max Range: 2.8049. Min Range: -2.8049

Max Act: 2.6791. Min Act: -0.1700

Data Index: 6761864 (Open Web Text)

Max Activating Token Index: 382

Text #15

Max Range: 2.8049. Min Range: -2.8049

Max Act: 2.6696. Min Act: -0.1700

Data Index: 5453090 (Open Web Text)

Max Activating Token Index: 347

Text #16

Max Range: 2.8049. Min Range: -2.8049

Max Act: 2.6823. Min Act: -0.1700

Data Index: 3320252 (Open Web Text)

Max Activating Token Index: 273

Text #17

Max Range: 2.8049. Min Range: -2.8049

Max Act: 2.6593. Min Act: -0.1700

Data Index: 7234035 (Open Web Text)

Max Activating Token Index: 899

Text #18

Max Range: 2.8049. Min Range: -2.8049

Max Act: 2.6726. Min Act: -0.1700

Data Index: 1972287 (Open Web Text)

Max Activating Token Index: 583

Text #19

Max Range: 2.8049. Min Range: -2.8049

Max Act: 2.6563. Min Act: -0.1700

Data Index: 4027773 (Open Web Text)

Max Activating Token Index: 907