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

Dataset: Open Web Text

Neuron 2057 in Layer 5

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: 4.4393. Min Range: -4.4393

Max Act: 4.4393. Min Act: -0.1700

Data Index: 6523097 (Open Web Text)

Max Activating Token Index: 295

Text #1

Max Range: 4.4393. Min Range: -4.4393

Max Act: 4.3193. Min Act: -0.1700

Data Index: 5207408 (Open Web Text)

Max Activating Token Index: 387

Text #2

Max Range: 4.4393. Min Range: -4.4393

Max Act: 4.2848. Min Act: -0.1700

Data Index: 5176138 (Open Web Text)

Max Activating Token Index: 153

Text #3

Max Range: 4.4393. Min Range: -4.4393

Max Act: 4.2975. Min Act: -0.1700

Data Index: 7576445 (Open Web Text)

Max Activating Token Index: 386

Text #4

Max Range: 4.4393. Min Range: -4.4393

Max Act: 4.2824. Min Act: -0.1700

Data Index: 3072446 (Open Web Text)

Max Activating Token Index: 240

Text #5

Max Range: 4.4393. Min Range: -4.4393

Max Act: 4.2377. Min Act: -0.1700

Data Index: 7640212 (Open Web Text)

Max Activating Token Index: 663

Text #6

Max Range: 4.4393. Min Range: -4.4393

Max Act: 4.2351. Min Act: -0.1700

Data Index: 7506067 (Open Web Text)

Max Activating Token Index: 554

Text #7

Max Range: 4.4393. Min Range: -4.4393

Max Act: 4.2160. Min Act: -0.1700

Data Index: 7158321 (Open Web Text)

Max Activating Token Index: 682

Text #8

Max Range: 4.4393. Min Range: -4.4393

Max Act: 4.2351. Min Act: -0.1700

Data Index: 5216353 (Open Web Text)

Max Activating Token Index: 392

Text #9

Max Range: 4.4393. Min Range: -4.4393

Max Act: 4.2339. Min Act: -0.1700

Data Index: 3151506 (Open Web Text)

Max Activating Token Index: 965

Text #10

Max Range: 4.4393. Min Range: -4.4393

Max Act: 4.2151. Min Act: -0.1700

Data Index: 5392269 (Open Web Text)

Max Activating Token Index: 225

Text #11

Max Range: 4.4393. Min Range: -4.4393

Max Act: 4.2156. Min Act: -0.1700

Data Index: 7244328 (Open Web Text)

Max Activating Token Index: 545

Text #12

Max Range: 4.4393. Min Range: -4.4393

Max Act: 4.1991. Min Act: -0.1700

Data Index: 3072445 (Open Web Text)

Max Activating Token Index: 510

Text #13

Max Range: 4.4393. Min Range: -4.4393

Max Act: 4.1892. Min Act: -0.1700

Data Index: 3492207 (Open Web Text)

Max Activating Token Index: 685

Text #14

Max Range: 4.4393. Min Range: -4.4393

Max Act: 4.1502. Min Act: -0.1700

Data Index: 7482572 (Open Web Text)

Max Activating Token Index: 672

Text #15

Max Range: 4.4393. Min Range: -4.4393

Max Act: 4.1503. Min Act: -0.1700

Data Index: 1660136 (Open Web Text)

Max Activating Token Index: 469

Text #16

Max Range: 4.4393. Min Range: -4.4393

Max Act: 4.1706. Min Act: -0.1700

Data Index: 5168168 (Open Web Text)

Max Activating Token Index: 944

Text #17

Max Range: 4.4393. Min Range: -4.4393

Max Act: 4.1329. Min Act: -0.1700

Data Index: 1421039 (Open Web Text)

Max Activating Token Index: 263

Text #18

Max Range: 4.4393. Min Range: -4.4393

Max Act: 4.1771. Min Act: -0.1700

Data Index: 5207920 (Open Web Text)

Max Activating Token Index: 1009

Text #19

Max Range: 4.4393. Min Range: -4.4393

Max Act: 4.1210. Min Act: -0.1700

Data Index: 5254255 (Open Web Text)

Max Activating Token Index: 303