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

Dataset: Open Web Text

Neuron 1657 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: 3.4667. Min Range: -3.4667

Max Act: 3.4667. Min Act: -0.1700

Data Index: 7468643 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.4667. Min Range: -3.4667

Max Act: 3.3559. Min Act: -0.1700

Data Index: 944063 (Open Web Text)

Max Activating Token Index: 666

Text #2

Max Range: 3.4667. Min Range: -3.4667

Max Act: 3.3309. Min Act: -0.1700

Data Index: 794978 (Open Web Text)

Max Activating Token Index: 418

Text #3

Max Range: 3.4667. Min Range: -3.4667

Max Act: 3.3627. Min Act: -0.1700

Data Index: 2493312 (Open Web Text)

Max Activating Token Index: 844

Text #4

Max Range: 3.4667. Min Range: -3.4667

Max Act: 3.2436. Min Act: -0.1700

Data Index: 915291 (Open Web Text)

Max Activating Token Index: 420

Text #5

Max Range: 3.4667. Min Range: -3.4667

Max Act: 3.2935. Min Act: -0.1700

Data Index: 1134854 (Open Web Text)

Max Activating Token Index: 998

Text #6

Max Range: 3.4667. Min Range: -3.4667

Max Act: 3.2772. Min Act: -0.1700

Data Index: 4555964 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 3.4667. Min Range: -3.4667

Max Act: 3.2644. Min Act: -0.1700

Data Index: 7176466 (Open Web Text)

Max Activating Token Index: 16

Text #8

Max Range: 3.4667. Min Range: -3.4667

Max Act: 3.2288. Min Act: -0.1700

Data Index: 4413825 (Open Web Text)

Max Activating Token Index: 426

Text #9

Max Range: 3.4667. Min Range: -3.4667

Max Act: 3.2139. Min Act: -0.1700

Data Index: 8215552 (Open Web Text)

Max Activating Token Index: 950

Text #10

Max Range: 3.4667. Min Range: -3.4667

Max Act: 3.2001. Min Act: -0.1700

Data Index: 227796 (Open Web Text)

Max Activating Token Index: 215

Text #11

Max Range: 3.4667. Min Range: -3.4667

Max Act: 3.2329. Min Act: -0.1700

Data Index: 734141 (Open Web Text)

Max Activating Token Index: 775

Text #12

Max Range: 3.4667. Min Range: -3.4667

Max Act: 3.2241. Min Act: -0.1700

Data Index: 1457769 (Open Web Text)

Max Activating Token Index: 1001

Text #13

Max Range: 3.4667. Min Range: -3.4667

Max Act: 3.2316. Min Act: -0.1700

Data Index: 8727289 (Open Web Text)

Max Activating Token Index: 560

Text #14

Max Range: 3.4667. Min Range: -3.4667

Max Act: 3.2347. Min Act: -0.1700

Data Index: 6396146 (Open Web Text)

Max Activating Token Index: 350

Text #15

Max Range: 3.4667. Min Range: -3.4667

Max Act: 3.1887. Min Act: -0.1700

Data Index: 317406 (Open Web Text)

Max Activating Token Index: 352

Text #16

Max Range: 3.4667. Min Range: -3.4667

Max Act: 3.2262. Min Act: -0.1700

Data Index: 4715109 (Open Web Text)

Max Activating Token Index: 301

Text #17

Max Range: 3.4667. Min Range: -3.4667

Max Act: 3.2031. Min Act: -0.1700

Data Index: 1828002 (Open Web Text)

Max Activating Token Index: 407

Text #18

Max Range: 3.4667. Min Range: -3.4667

Max Act: 3.2361. Min Act: -0.1700

Data Index: 2193165 (Open Web Text)

Max Activating Token Index: 426

Text #19

Max Range: 3.4667. Min Range: -3.4667

Max Act: 3.2159. Min Act: -0.1700

Data Index: 1952664 (Open Web Text)

Max Activating Token Index: 95