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

Dataset: Open Web Text

Neuron 2176 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: 4.0467. Min Range: -4.0467

Max Act: 4.0461. Min Act: -0.1700

Data Index: 3347051 (Open Web Text)

Max Activating Token Index: 461

Text #1

Max Range: 4.0467. Min Range: -4.0467

Max Act: 4.0467. Min Act: -0.1700

Data Index: 8705502 (Open Web Text)

Max Activating Token Index: 439

Text #2

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.9781. Min Act: -0.1700

Data Index: 1583273 (Open Web Text)

Max Activating Token Index: 517

Text #3

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.9981. Min Act: -0.1700

Data Index: 1609588 (Open Web Text)

Max Activating Token Index: 234

Text #4

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.9961. Min Act: -0.1700

Data Index: 968601 (Open Web Text)

Max Activating Token Index: 328

Text #5

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.9749. Min Act: -0.1700

Data Index: 4282553 (Open Web Text)

Max Activating Token Index: 624

Text #6

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.9497. Min Act: -0.1700

Data Index: 4064429 (Open Web Text)

Max Activating Token Index: 359

Text #7

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.9468. Min Act: -0.1700

Data Index: 3446170 (Open Web Text)

Max Activating Token Index: 612

Text #8

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.9161. Min Act: -0.1700

Data Index: 6180394 (Open Web Text)

Max Activating Token Index: 31

Text #9

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.9405. Min Act: -0.1700

Data Index: 2425737 (Open Web Text)

Max Activating Token Index: 384

Text #10

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.9262. Min Act: -0.1700

Data Index: 8658204 (Open Web Text)

Max Activating Token Index: 509

Text #11

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.9104. Min Act: -0.1700

Data Index: 7408858 (Open Web Text)

Max Activating Token Index: 536

Text #12

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.9237. Min Act: -0.1700

Data Index: 3096890 (Open Web Text)

Max Activating Token Index: 194

Text #13

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.9448. Min Act: -0.1700

Data Index: 1998016 (Open Web Text)

Max Activating Token Index: 727

Text #14

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.8844. Min Act: -0.1700

Data Index: 3249136 (Open Web Text)

Max Activating Token Index: 862

Text #15

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.9182. Min Act: -0.1700

Data Index: 1866933 (Open Web Text)

Max Activating Token Index: 90

Text #16

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.9206. Min Act: -0.1700

Data Index: 2474814 (Open Web Text)

Max Activating Token Index: 715

Text #17

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.8871. Min Act: -0.1700

Data Index: 5048008 (Open Web Text)

Max Activating Token Index: 529

Text #18

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.8954. Min Act: -0.1700

Data Index: 5349979 (Open Web Text)

Max Activating Token Index: 527

Text #19

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.8803. Min Act: -0.1700

Data Index: 6626300 (Open Web Text)

Max Activating Token Index: 857