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

Dataset: Open Web Text

Neuron 1501 in Layer 2

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: 4.8285. Min Range: -4.8285

Max Act: 4.8285. Min Act: -0.1700

Data Index: 6850807 (Open Web Text)

Max Activating Token Index: 561

Text #1

Max Range: 4.8285. Min Range: -4.8285

Max Act: 4.7632. Min Act: -0.1700

Data Index: 4355648 (Open Web Text)

Max Activating Token Index: 138

Text #2

Max Range: 4.8285. Min Range: -4.8285

Max Act: 4.7437. Min Act: -0.1700

Data Index: 6338952 (Open Web Text)

Max Activating Token Index: 615

Text #3

Max Range: 4.8285. Min Range: -4.8285

Max Act: 4.7086. Min Act: -0.1700

Data Index: 2345942 (Open Web Text)

Max Activating Token Index: 887

Text #4

Max Range: 4.8285. Min Range: -4.8285

Max Act: 4.7205. Min Act: -0.1700

Data Index: 7885603 (Open Web Text)

Max Activating Token Index: 128

Text #5

Max Range: 4.8285. Min Range: -4.8285

Max Act: 4.6645. Min Act: -0.1700

Data Index: 2345951 (Open Web Text)

Max Activating Token Index: 139

Text #6

Max Range: 4.8285. Min Range: -4.8285

Max Act: 4.7197. Min Act: -0.1700

Data Index: 8222599 (Open Web Text)

Max Activating Token Index: 108

Text #7

Max Range: 4.8285. Min Range: -4.8285

Max Act: 4.6289. Min Act: -0.1700

Data Index: 2359325 (Open Web Text)

Max Activating Token Index: 292

Text #8

Max Range: 4.8285. Min Range: -4.8285

Max Act: 4.6379. Min Act: -0.1700

Data Index: 8330821 (Open Web Text)

Max Activating Token Index: 250

Text #9

Max Range: 4.8285. Min Range: -4.8285

Max Act: 4.5982. Min Act: -0.1700

Data Index: 7834783 (Open Web Text)

Max Activating Token Index: 157

Text #10

Max Range: 4.8285. Min Range: -4.8285

Max Act: 4.6248. Min Act: -0.1700

Data Index: 5890006 (Open Web Text)

Max Activating Token Index: 798

Text #11

Max Range: 4.8285. Min Range: -4.8285

Max Act: 4.5597. Min Act: -0.1700

Data Index: 2133072 (Open Web Text)

Max Activating Token Index: 192

Text #12

Max Range: 4.8285. Min Range: -4.8285

Max Act: 4.5805. Min Act: -0.1700

Data Index: 4357397 (Open Web Text)

Max Activating Token Index: 38

Text #13

Max Range: 4.8285. Min Range: -4.8285

Max Act: 4.6289. Min Act: -0.1700

Data Index: 4056281 (Open Web Text)

Max Activating Token Index: 738

Text #14

Max Range: 4.8285. Min Range: -4.8285

Max Act: 4.5967. Min Act: -0.1700

Data Index: 3500877 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 4.8285. Min Range: -4.8285

Max Act: 4.5825. Min Act: -0.1700

Data Index: 564200 (Open Web Text)

Max Activating Token Index: 387

Text #16

Max Range: 4.8285. Min Range: -4.8285

Max Act: 4.5478. Min Act: -0.1700

Data Index: 7267252 (Open Web Text)

Max Activating Token Index: 581

Text #17

Max Range: 4.8285. Min Range: -4.8285

Max Act: 4.5526. Min Act: -0.1700

Data Index: 4355652 (Open Web Text)

Max Activating Token Index: 489

Text #18

Max Range: 4.8285. Min Range: -4.8285

Max Act: 4.5535. Min Act: -0.1700

Data Index: 5629004 (Open Web Text)

Max Activating Token Index: 532

Text #19

Max Range: 4.8285. Min Range: -4.8285

Max Act: 4.5234. Min Act: -0.1700

Data Index: 3949916 (Open Web Text)

Max Activating Token Index: 555