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

Dataset: Open Web Text

Neuron 1275 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: 1.8317. Min Range: -1.8317

Max Act: 1.8317. Min Act: -0.1700

Data Index: 8243171 (Open Web Text)

Max Activating Token Index: 114

Text #1

Max Range: 1.8317. Min Range: -1.8317

Max Act: 1.7975. Min Act: -0.1700

Data Index: 5226344 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 1.8317. Min Range: -1.8317

Max Act: 1.8013. Min Act: -0.1700

Data Index: 5905082 (Open Web Text)

Max Activating Token Index: 284

Text #3

Max Range: 1.8317. Min Range: -1.8317

Max Act: 1.7910. Min Act: -0.1700

Data Index: 6811759 (Open Web Text)

Max Activating Token Index: 25

Text #4

Max Range: 1.8317. Min Range: -1.8317

Max Act: 1.7866. Min Act: -0.1700

Data Index: 6882935 (Open Web Text)

Max Activating Token Index: 56

Text #5

Max Range: 1.8317. Min Range: -1.8317

Max Act: 1.7858. Min Act: -0.1700

Data Index: 3754930 (Open Web Text)

Max Activating Token Index: 226

Text #6

Max Range: 1.8317. Min Range: -1.8317

Max Act: 1.7715. Min Act: -0.1700

Data Index: 4002450 (Open Web Text)

Max Activating Token Index: 489

Text #7

Max Range: 1.8317. Min Range: -1.8317

Max Act: 1.7740. Min Act: -0.1700

Data Index: 438983 (Open Web Text)

Max Activating Token Index: 598

Text #8

Max Range: 1.8317. Min Range: -1.8317

Max Act: 1.7657. Min Act: -0.1700

Data Index: 7811762 (Open Web Text)

Max Activating Token Index: 117

Text #9

Max Range: 1.8317. Min Range: -1.8317

Max Act: 1.7326. Min Act: -0.1700

Data Index: 5489578 (Open Web Text)

Max Activating Token Index: 63

Text #10

Max Range: 1.8317. Min Range: -1.8317

Max Act: 1.7333. Min Act: -0.1700

Data Index: 2335524 (Open Web Text)

Max Activating Token Index: 87

Text #11

Max Range: 1.8317. Min Range: -1.8317

Max Act: 1.7338. Min Act: -0.1700

Data Index: 1749697 (Open Web Text)

Max Activating Token Index: 139

Text #12

Max Range: 1.8317. Min Range: -1.8317

Max Act: 1.7426. Min Act: -0.1700

Data Index: 2762534 (Open Web Text)

Max Activating Token Index: 20

Text #13

Max Range: 1.8317. Min Range: -1.8317

Max Act: 1.7444. Min Act: -0.1700

Data Index: 5902503 (Open Web Text)

Max Activating Token Index: 797

Text #14

Max Range: 1.8317. Min Range: -1.8317

Max Act: 1.7319. Min Act: -0.1700

Data Index: 3293202 (Open Web Text)

Max Activating Token Index: 84

Text #15

Max Range: 1.8317. Min Range: -1.8317

Max Act: 1.7334. Min Act: -0.1700

Data Index: 1407153 (Open Web Text)

Max Activating Token Index: 274

Text #16

Max Range: 1.8317. Min Range: -1.8317

Max Act: 1.7252. Min Act: -0.1700

Data Index: 121244 (Open Web Text)

Max Activating Token Index: 322

Text #17

Max Range: 1.8317. Min Range: -1.8317

Max Act: 1.7187. Min Act: -0.1700

Data Index: 6647885 (Open Web Text)

Max Activating Token Index: 980

Text #18

Max Range: 1.8317. Min Range: -1.8317

Max Act: 1.7181. Min Act: -0.1700

Data Index: 6677469 (Open Web Text)

Max Activating Token Index: 484

Text #19

Max Range: 1.8317. Min Range: -1.8317

Max Act: 1.7128. Min Act: -0.1700

Data Index: 958595 (Open Web Text)

Max Activating Token Index: 119