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

Dataset: Open Web Text

Neuron 2862 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: 4.2424. Min Range: -4.2424

Max Act: 4.2424. Min Act: -0.1700

Data Index: 6371747 (Open Web Text)

Max Activating Token Index: 960

Text #1

Max Range: 4.2424. Min Range: -4.2424

Max Act: 4.2256. Min Act: -0.1700

Data Index: 4474046 (Open Web Text)

Max Activating Token Index: 422

Text #2

Max Range: 4.2424. Min Range: -4.2424

Max Act: 4.1993. Min Act: -0.1700

Data Index: 760713 (Open Web Text)

Max Activating Token Index: 282

Text #3

Max Range: 4.2424. Min Range: -4.2424

Max Act: 4.1751. Min Act: -0.1700

Data Index: 1907583 (Open Web Text)

Max Activating Token Index: 565

Text #4

Max Range: 4.2424. Min Range: -4.2424

Max Act: 4.1674. Min Act: -0.1700

Data Index: 8140570 (Open Web Text)

Max Activating Token Index: 265

Text #5

Max Range: 4.2424. Min Range: -4.2424

Max Act: 4.1414. Min Act: -0.1700

Data Index: 8725935 (Open Web Text)

Max Activating Token Index: 399

Text #6

Max Range: 4.2424. Min Range: -4.2424

Max Act: 4.1225. Min Act: -0.1700

Data Index: 7890753 (Open Web Text)

Max Activating Token Index: 518

Text #7

Max Range: 4.2424. Min Range: -4.2424

Max Act: 4.1169. Min Act: -0.1700

Data Index: 738536 (Open Web Text)

Max Activating Token Index: 267

Text #8

Max Range: 4.2424. Min Range: -4.2424

Max Act: 4.1472. Min Act: -0.1700

Data Index: 6585215 (Open Web Text)

Max Activating Token Index: 823

Text #9

Max Range: 4.2424. Min Range: -4.2424

Max Act: 4.1291. Min Act: -0.1700

Data Index: 793055 (Open Web Text)

Max Activating Token Index: 604

Text #10

Max Range: 4.2424. Min Range: -4.2424

Max Act: 4.1472. Min Act: -0.1700

Data Index: 8120172 (Open Web Text)

Max Activating Token Index: 498

Text #11

Max Range: 4.2424. Min Range: -4.2424

Max Act: 4.1209. Min Act: -0.1700

Data Index: 7381415 (Open Web Text)

Max Activating Token Index: 336

Text #12

Max Range: 4.2424. Min Range: -4.2424

Max Act: 4.1272. Min Act: -0.1700

Data Index: 5100995 (Open Web Text)

Max Activating Token Index: 228

Text #13

Max Range: 4.2424. Min Range: -4.2424

Max Act: 4.1163. Min Act: -0.1700

Data Index: 7203321 (Open Web Text)

Max Activating Token Index: 341

Text #14

Max Range: 4.2424. Min Range: -4.2424

Max Act: 4.1080. Min Act: -0.1700

Data Index: 1629000 (Open Web Text)

Max Activating Token Index: 243

Text #15

Max Range: 4.2424. Min Range: -4.2424

Max Act: 4.1162. Min Act: -0.1700

Data Index: 1524687 (Open Web Text)

Max Activating Token Index: 39

Text #16

Max Range: 4.2424. Min Range: -4.2424

Max Act: 4.1140. Min Act: -0.1700

Data Index: 7986710 (Open Web Text)

Max Activating Token Index: 142

Text #17

Max Range: 4.2424. Min Range: -4.2424

Max Act: 4.0926. Min Act: -0.1700

Data Index: 7176548 (Open Web Text)

Max Activating Token Index: 78

Text #18

Max Range: 4.2424. Min Range: -4.2424

Max Act: 4.1355. Min Act: -0.1700

Data Index: 1740547 (Open Web Text)

Max Activating Token Index: 555

Text #19

Max Range: 4.2424. Min Range: -4.2424

Max Act: 4.1185. Min Act: -0.1700

Data Index: 1476533 (Open Web Text)

Max Activating Token Index: 181