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

Dataset: Open Web Text

Neuron 1311 in Layer 1

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: 1.5597. Min Range: -1.5597

Max Act: 1.5597. Min Act: -0.1700

Data Index: 6685475 (Open Web Text)

Max Activating Token Index: 842

Text #1

Max Range: 1.5597. Min Range: -1.5597

Max Act: 1.5556. Min Act: -0.1700

Data Index: 2412430 (Open Web Text)

Max Activating Token Index: 116

Text #2

Max Range: 1.5597. Min Range: -1.5597

Max Act: 1.5459. Min Act: -0.1700

Data Index: 2622573 (Open Web Text)

Max Activating Token Index: 493

Text #3

Max Range: 1.5597. Min Range: -1.5597

Max Act: 1.5448. Min Act: -0.1700

Data Index: 4017776 (Open Web Text)

Max Activating Token Index: 21

Text #4

Max Range: 1.5597. Min Range: -1.5597

Max Act: 1.5483. Min Act: -0.1700

Data Index: 8407091 (Open Web Text)

Max Activating Token Index: 130

Text #5

Max Range: 1.5597. Min Range: -1.5597

Max Act: 1.5467. Min Act: -0.1700

Data Index: 7299975 (Open Web Text)

Max Activating Token Index: 20

Text #6

Max Range: 1.5597. Min Range: -1.5597

Max Act: 1.5385. Min Act: -0.1700

Data Index: 5706159 (Open Web Text)

Max Activating Token Index: 21

Text #7

Max Range: 1.5597. Min Range: -1.5597

Max Act: 1.5369. Min Act: -0.1700

Data Index: 2960153 (Open Web Text)

Max Activating Token Index: 13

Text #8

Max Range: 1.5597. Min Range: -1.5597

Max Act: 1.5343. Min Act: -0.1700

Data Index: 6425392 (Open Web Text)

Max Activating Token Index: 640

Text #9

Max Range: 1.5597. Min Range: -1.5597

Max Act: 1.5390. Min Act: -0.1700

Data Index: 5441262 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 1.5597. Min Range: -1.5597

Max Act: 1.5310. Min Act: -0.1700

Data Index: 5579676 (Open Web Text)

Max Activating Token Index: 208

Text #11

Max Range: 1.5597. Min Range: -1.5597

Max Act: 1.5328. Min Act: -0.1700

Data Index: 3416686 (Open Web Text)

Max Activating Token Index: 29

Text #12

Max Range: 1.5597. Min Range: -1.5597

Max Act: 1.5274. Min Act: -0.1700

Data Index: 5980552 (Open Web Text)

Max Activating Token Index: 209

Text #13

Max Range: 1.5597. Min Range: -1.5597

Max Act: 1.5309. Min Act: -0.1700

Data Index: 2031829 (Open Web Text)

Max Activating Token Index: 34

Text #14

Max Range: 1.5597. Min Range: -1.5597

Max Act: 1.5291. Min Act: -0.1699

Data Index: 8317355 (Open Web Text)

Max Activating Token Index: 132

Text #15

Max Range: 1.5597. Min Range: -1.5597

Max Act: 1.5196. Min Act: -0.1700

Data Index: 7533681 (Open Web Text)

Max Activating Token Index: 66

Text #16

Max Range: 1.5597. Min Range: -1.5597

Max Act: 1.5187. Min Act: -0.1700

Data Index: 358974 (Open Web Text)

Max Activating Token Index: 451

Text #17

Max Range: 1.5597. Min Range: -1.5597

Max Act: 1.5160. Min Act: -0.1700

Data Index: 7282330 (Open Web Text)

Max Activating Token Index: 13

Text #18

Max Range: 1.5597. Min Range: -1.5597

Max Act: 1.5229. Min Act: -0.1700

Data Index: 1835080 (Open Web Text)

Max Activating Token Index: 891

Text #19

Max Range: 1.5597. Min Range: -1.5597

Max Act: 1.5204. Min Act: -0.1700

Data Index: 1732435 (Open Web Text)

Max Activating Token Index: 163