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

Dataset: Open Web Text

Neuron 659 in Layer 0

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: 1.0912. Min Range: -1.0912

Max Act: 1.0849. Min Act: -0.1700

Data Index: 8322929 (Open Web Text)

Max Activating Token Index: 300

Text #1

Max Range: 1.0912. Min Range: -1.0912

Max Act: 1.0912. Min Act: -0.1700

Data Index: 961746 (Open Web Text)

Max Activating Token Index: 281

Text #2

Max Range: 1.0912. Min Range: -1.0912

Max Act: 1.0594. Min Act: -0.1700

Data Index: 3234306 (Open Web Text)

Max Activating Token Index: 302

Text #3

Max Range: 1.0912. Min Range: -1.0912

Max Act: 1.0638. Min Act: -0.1700

Data Index: 3443160 (Open Web Text)

Max Activating Token Index: 304

Text #4

Max Range: 1.0912. Min Range: -1.0912

Max Act: 1.0685. Min Act: -0.1700

Data Index: 3693249 (Open Web Text)

Max Activating Token Index: 298

Text #5

Max Range: 1.0912. Min Range: -1.0912

Max Act: 1.0730. Min Act: -0.1700

Data Index: 1861000 (Open Web Text)

Max Activating Token Index: 287

Text #6

Max Range: 1.0912. Min Range: -1.0912

Max Act: 1.0704. Min Act: -0.1700

Data Index: 5948293 (Open Web Text)

Max Activating Token Index: 295

Text #7

Max Range: 1.0912. Min Range: -1.0912

Max Act: 1.0637. Min Act: -0.1700

Data Index: 5699838 (Open Web Text)

Max Activating Token Index: 285

Text #8

Max Range: 1.0912. Min Range: -1.0912

Max Act: 1.0698. Min Act: -0.1700

Data Index: 111426 (Open Web Text)

Max Activating Token Index: 300

Text #9

Max Range: 1.0912. Min Range: -1.0912

Max Act: 1.0567. Min Act: -0.1700

Data Index: 5387086 (Open Web Text)

Max Activating Token Index: 296

Text #10

Max Range: 1.0912. Min Range: -1.0912

Max Act: 1.0467. Min Act: -0.1700

Data Index: 2912806 (Open Web Text)

Max Activating Token Index: 290

Text #11

Max Range: 1.0912. Min Range: -1.0912

Max Act: 1.0488. Min Act: -0.1700

Data Index: 2541832 (Open Web Text)

Max Activating Token Index: 293

Text #12

Max Range: 1.0912. Min Range: -1.0912

Max Act: 1.0526. Min Act: -0.1700

Data Index: 2180544 (Open Web Text)

Max Activating Token Index: 286

Text #13

Max Range: 1.0912. Min Range: -1.0912

Max Act: 1.0475. Min Act: -0.1700

Data Index: 718794 (Open Web Text)

Max Activating Token Index: 308

Text #14

Max Range: 1.0912. Min Range: -1.0912

Max Act: 1.0605. Min Act: -0.1700

Data Index: 4660827 (Open Web Text)

Max Activating Token Index: 306

Text #15

Max Range: 1.0912. Min Range: -1.0912

Max Act: 1.0573. Min Act: -0.1700

Data Index: 3871557 (Open Web Text)

Max Activating Token Index: 303

Text #16

Max Range: 1.0912. Min Range: -1.0912

Max Act: 1.0535. Min Act: -0.1700

Data Index: 3432432 (Open Web Text)

Max Activating Token Index: 306

Text #17

Max Range: 1.0912. Min Range: -1.0912

Max Act: 1.0532. Min Act: -0.1700

Data Index: 654296 (Open Web Text)

Max Activating Token Index: 311

Text #18

Max Range: 1.0912. Min Range: -1.0912

Max Act: 1.0598. Min Act: -0.1700

Data Index: 3020605 (Open Web Text)

Max Activating Token Index: 291

Text #19

Max Range: 1.0912. Min Range: -1.0912

Max Act: 1.0301. Min Act: -0.1700

Data Index: 2695038 (Open Web Text)

Max Activating Token Index: 298