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

Dataset: Open Web Text

Neuron 1493 in Layer 3

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: 3.1031. Min Range: -3.1031

Max Act: 3.1031. Min Act: -0.1700

Data Index: 6914898 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 3.1031. Min Range: -3.1031

Max Act: 3.0568. Min Act: -0.1700

Data Index: 1719765 (Open Web Text)

Max Activating Token Index: 554

Text #2

Max Range: 3.1031. Min Range: -3.1031

Max Act: 3.0096. Min Act: -0.1700

Data Index: 8070188 (Open Web Text)

Max Activating Token Index: 620

Text #3

Max Range: 3.1031. Min Range: -3.1031

Max Act: 3.0172. Min Act: -0.1700

Data Index: 2413053 (Open Web Text)

Max Activating Token Index: 788

Text #4

Max Range: 3.1031. Min Range: -3.1031

Max Act: 2.9714. Min Act: -0.1700

Data Index: 6086405 (Open Web Text)

Max Activating Token Index: 549

Text #5

Max Range: 3.1031. Min Range: -3.1031

Max Act: 2.9871. Min Act: -0.1700

Data Index: 3876535 (Open Web Text)

Max Activating Token Index: 557

Text #6

Max Range: 3.1031. Min Range: -3.1031

Max Act: 2.9654. Min Act: -0.1700

Data Index: 2707723 (Open Web Text)

Max Activating Token Index: 859

Text #7

Max Range: 3.1031. Min Range: -3.1031

Max Act: 2.9676. Min Act: -0.1700

Data Index: 1814855 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 3.1031. Min Range: -3.1031

Max Act: 2.9785. Min Act: -0.1700

Data Index: 3398540 (Open Web Text)

Max Activating Token Index: 710

Text #9

Max Range: 3.1031. Min Range: -3.1031

Max Act: 2.9643. Min Act: -0.1700

Data Index: 2544612 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 3.1031. Min Range: -3.1031

Max Act: 2.9480. Min Act: -0.1700

Data Index: 852652 (Open Web Text)

Max Activating Token Index: 517

Text #11

Max Range: 3.1031. Min Range: -3.1031

Max Act: 2.9401. Min Act: -0.1700

Data Index: 5622217 (Open Web Text)

Max Activating Token Index: 632

Text #12

Max Range: 3.1031. Min Range: -3.1031

Max Act: 2.9511. Min Act: -0.1700

Data Index: 8474081 (Open Web Text)

Max Activating Token Index: 43

Text #13

Max Range: 3.1031. Min Range: -3.1031

Max Act: 2.9359. Min Act: -0.1700

Data Index: 8194749 (Open Web Text)

Max Activating Token Index: 141

Text #14

Max Range: 3.1031. Min Range: -3.1031

Max Act: 2.9241. Min Act: -0.1700

Data Index: 1374071 (Open Web Text)

Max Activating Token Index: 343

Text #15

Max Range: 3.1031. Min Range: -3.1031

Max Act: 2.9361. Min Act: -0.1700

Data Index: 7439790 (Open Web Text)

Max Activating Token Index: 182

Text #16

Max Range: 3.1031. Min Range: -3.1031

Max Act: 2.9157. Min Act: -0.1700

Data Index: 2530634 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.1031. Min Range: -3.1031

Max Act: 2.9345. Min Act: -0.1700

Data Index: 4196162 (Open Web Text)

Max Activating Token Index: 592

Text #18

Max Range: 3.1031. Min Range: -3.1031

Max Act: 2.9276. Min Act: -0.1700

Data Index: 7121062 (Open Web Text)

Max Activating Token Index: 378

Text #19

Max Range: 3.1031. Min Range: -3.1031

Max Act: 2.9157. Min Act: -0.1700

Data Index: 2094715 (Open Web Text)

Max Activating Token Index: 4