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

Dataset: Open Web Text

Neuron 2905 in Layer 6

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: 3.2480. Min Range: -3.2480

Max Act: 3.2480. Min Act: -0.1700

Data Index: 2454343 (Open Web Text)

Max Activating Token Index: 557

Text #1

Max Range: 3.2480. Min Range: -3.2480

Max Act: 3.2269. Min Act: -0.1700

Data Index: 4882368 (Open Web Text)

Max Activating Token Index: 244

Text #2

Max Range: 3.2480. Min Range: -3.2480

Max Act: 3.1890. Min Act: -0.1700

Data Index: 987111 (Open Web Text)

Max Activating Token Index: 290

Text #3

Max Range: 3.2480. Min Range: -3.2480

Max Act: 3.2235. Min Act: -0.1700

Data Index: 5663136 (Open Web Text)

Max Activating Token Index: 403

Text #4

Max Range: 3.2480. Min Range: -3.2480

Max Act: 3.1807. Min Act: -0.1700

Data Index: 136678 (Open Web Text)

Max Activating Token Index: 323

Text #5

Max Range: 3.2480. Min Range: -3.2480

Max Act: 3.1512. Min Act: -0.1700

Data Index: 5122774 (Open Web Text)

Max Activating Token Index: 921

Text #6

Max Range: 3.2480. Min Range: -3.2480

Max Act: 3.1279. Min Act: -0.1700

Data Index: 399998 (Open Web Text)

Max Activating Token Index: 380

Text #7

Max Range: 3.2480. Min Range: -3.2480

Max Act: 3.1301. Min Act: -0.1700

Data Index: 8198565 (Open Web Text)

Max Activating Token Index: 714

Text #8

Max Range: 3.2480. Min Range: -3.2480

Max Act: 3.0847. Min Act: -0.1700

Data Index: 1854508 (Open Web Text)

Max Activating Token Index: 347

Text #9

Max Range: 3.2480. Min Range: -3.2480

Max Act: 3.0809. Min Act: -0.1700

Data Index: 7654657 (Open Web Text)

Max Activating Token Index: 340

Text #10

Max Range: 3.2480. Min Range: -3.2480

Max Act: 3.0841. Min Act: -0.1700

Data Index: 6393697 (Open Web Text)

Max Activating Token Index: 987

Text #11

Max Range: 3.2480. Min Range: -3.2480

Max Act: 3.0621. Min Act: -0.1700

Data Index: 4133151 (Open Web Text)

Max Activating Token Index: 577

Text #12

Max Range: 3.2480. Min Range: -3.2480

Max Act: 3.0620. Min Act: -0.1700

Data Index: 2000039 (Open Web Text)

Max Activating Token Index: 445

Text #13

Max Range: 3.2480. Min Range: -3.2480

Max Act: 3.0476. Min Act: -0.1700

Data Index: 6732185 (Open Web Text)

Max Activating Token Index: 426

Text #14

Max Range: 3.2480. Min Range: -3.2480

Max Act: 3.0509. Min Act: -0.1700

Data Index: 2519517 (Open Web Text)

Max Activating Token Index: 431

Text #15

Max Range: 3.2480. Min Range: -3.2480

Max Act: 3.0534. Min Act: -0.1700

Data Index: 7038423 (Open Web Text)

Max Activating Token Index: 580

Text #16

Max Range: 3.2480. Min Range: -3.2480

Max Act: 3.0324. Min Act: -0.1700

Data Index: 7708691 (Open Web Text)

Max Activating Token Index: 403

Text #17

Max Range: 3.2480. Min Range: -3.2480

Max Act: 3.0290. Min Act: -0.1700

Data Index: 4472651 (Open Web Text)

Max Activating Token Index: 414

Text #18

Max Range: 3.2480. Min Range: -3.2480

Max Act: 3.0397. Min Act: -0.1700

Data Index: 165659 (Open Web Text)

Max Activating Token Index: 208

Text #19

Max Range: 3.2480. Min Range: -3.2480

Max Act: 3.0465. Min Act: -0.1700

Data Index: 2949467 (Open Web Text)

Max Activating Token Index: 1018