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

Dataset: Open Web Text

Neuron 2156 in Layer 0

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: 2.7599. Min Range: -2.7599

Max Act: 2.7599. Min Act: -0.1700

Data Index: 5377352 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 2.7599. Min Range: -2.7599

Max Act: 2.7341. Min Act: -0.1700

Data Index: 4694361 (Open Web Text)

Max Activating Token Index: 13

Text #2

Max Range: 2.7599. Min Range: -2.7599

Max Act: 2.7192. Min Act: -0.1700

Data Index: 550052 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 2.7599. Min Range: -2.7599

Max Act: 2.6951. Min Act: -0.1700

Data Index: 3469248 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 2.7599. Min Range: -2.7599

Max Act: 2.7019. Min Act: -0.1700

Data Index: 89420 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 2.7599. Min Range: -2.7599

Max Act: 2.6637. Min Act: -0.1700

Data Index: 287764 (Open Web Text)

Max Activating Token Index: 17

Text #6

Max Range: 2.7599. Min Range: -2.7599

Max Act: 2.6564. Min Act: -0.1700

Data Index: 8598461 (Open Web Text)

Max Activating Token Index: 13

Text #7

Max Range: 2.7599. Min Range: -2.7599

Max Act: 2.6516. Min Act: -0.1700

Data Index: 4725511 (Open Web Text)

Max Activating Token Index: 15

Text #8

Max Range: 2.7599. Min Range: -2.7599

Max Act: 2.6424. Min Act: -0.1700

Data Index: 8699415 (Open Web Text)

Max Activating Token Index: 16

Text #9

Max Range: 2.7599. Min Range: -2.7599

Max Act: 2.6335. Min Act: -0.1700

Data Index: 6510507 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 2.7599. Min Range: -2.7599

Max Act: 2.6401. Min Act: -0.1700

Data Index: 4112884 (Open Web Text)

Max Activating Token Index: 20

Text #11

Max Range: 2.7599. Min Range: -2.7599

Max Act: 2.6319. Min Act: -0.1700

Data Index: 4036321 (Open Web Text)

Max Activating Token Index: 446

Text #12

Max Range: 2.7599. Min Range: -2.7599

Max Act: 2.6480. Min Act: -0.1700

Data Index: 5541604 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 2.7599. Min Range: -2.7599

Max Act: 2.6356. Min Act: -0.1700

Data Index: 3285595 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 2.7599. Min Range: -2.7599

Max Act: 2.6366. Min Act: -0.1700

Data Index: 3152595 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 2.7599. Min Range: -2.7599

Max Act: 2.6279. Min Act: -0.1700

Data Index: 8574422 (Open Web Text)

Max Activating Token Index: 16

Text #16

Max Range: 2.7599. Min Range: -2.7599

Max Act: 2.6173. Min Act: -0.1700

Data Index: 3761228 (Open Web Text)

Max Activating Token Index: 286

Text #17

Max Range: 2.7599. Min Range: -2.7599

Max Act: 2.6275. Min Act: -0.1700

Data Index: 7961154 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 2.7599. Min Range: -2.7599

Max Act: 2.6254. Min Act: -0.1700

Data Index: 3448961 (Open Web Text)

Max Activating Token Index: 25

Text #19

Max Range: 2.7599. Min Range: -2.7599

Max Act: 2.6262. Min Act: -0.1700

Data Index: 7418809 (Open Web Text)

Max Activating Token Index: 4