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

Dataset: Open Web Text

Neuron 2885 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: 3.5142. Min Range: -3.5142

Max Act: 3.5142. Min Act: -0.1700

Data Index: 3564673 (Open Web Text)

Max Activating Token Index: 327

Text #1

Max Range: 3.5142. Min Range: -3.5142

Max Act: 3.4949. Min Act: -0.1700

Data Index: 7709636 (Open Web Text)

Max Activating Token Index: 1004

Text #2

Max Range: 3.5142. Min Range: -3.5142

Max Act: 3.4448. Min Act: -0.1700

Data Index: 1483837 (Open Web Text)

Max Activating Token Index: 455

Text #3

Max Range: 3.5142. Min Range: -3.5142

Max Act: 3.4567. Min Act: -0.1700

Data Index: 5078765 (Open Web Text)

Max Activating Token Index: 995

Text #4

Max Range: 3.5142. Min Range: -3.5142

Max Act: 3.4346. Min Act: -0.1700

Data Index: 6208457 (Open Web Text)

Max Activating Token Index: 596

Text #5

Max Range: 3.5142. Min Range: -3.5142

Max Act: 3.4391. Min Act: -0.1700

Data Index: 6185948 (Open Web Text)

Max Activating Token Index: 824

Text #6

Max Range: 3.5142. Min Range: -3.5142

Max Act: 3.4365. Min Act: -0.1700

Data Index: 3622510 (Open Web Text)

Max Activating Token Index: 167

Text #7

Max Range: 3.5142. Min Range: -3.5142

Max Act: 3.4306. Min Act: -0.1700

Data Index: 7379004 (Open Web Text)

Max Activating Token Index: 600

Text #8

Max Range: 3.5142. Min Range: -3.5142

Max Act: 3.4130. Min Act: -0.1700

Data Index: 2201281 (Open Web Text)

Max Activating Token Index: 511

Text #9

Max Range: 3.5142. Min Range: -3.5142

Max Act: 3.3934. Min Act: -0.1700

Data Index: 123953 (Open Web Text)

Max Activating Token Index: 697

Text #10

Max Range: 3.5142. Min Range: -3.5142

Max Act: 3.3746. Min Act: -0.1700

Data Index: 415692 (Open Web Text)

Max Activating Token Index: 817

Text #11

Max Range: 3.5142. Min Range: -3.5142

Max Act: 3.3638. Min Act: -0.1700

Data Index: 3710711 (Open Web Text)

Max Activating Token Index: 657

Text #12

Max Range: 3.5142. Min Range: -3.5142

Max Act: 3.3752. Min Act: -0.1700

Data Index: 4549192 (Open Web Text)

Max Activating Token Index: 256

Text #13

Max Range: 3.5142. Min Range: -3.5142

Max Act: 3.3717. Min Act: -0.1700

Data Index: 2690415 (Open Web Text)

Max Activating Token Index: 510

Text #14

Max Range: 3.5142. Min Range: -3.5142

Max Act: 3.3681. Min Act: -0.1700

Data Index: 6125625 (Open Web Text)

Max Activating Token Index: 304

Text #15

Max Range: 3.5142. Min Range: -3.5142

Max Act: 3.3765. Min Act: -0.1700

Data Index: 7972766 (Open Web Text)

Max Activating Token Index: 536

Text #16

Max Range: 3.5142. Min Range: -3.5142

Max Act: 3.3660. Min Act: -0.1700

Data Index: 1628436 (Open Web Text)

Max Activating Token Index: 385

Text #17

Max Range: 3.5142. Min Range: -3.5142

Max Act: 3.3566. Min Act: -0.1700

Data Index: 2697514 (Open Web Text)

Max Activating Token Index: 828

Text #18

Max Range: 3.5142. Min Range: -3.5142

Max Act: 3.3756. Min Act: -0.1700

Data Index: 6379039 (Open Web Text)

Max Activating Token Index: 563

Text #19

Max Range: 3.5142. Min Range: -3.5142

Max Act: 3.3698. Min Act: -0.1700

Data Index: 8196598 (Open Web Text)

Max Activating Token Index: 920