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

Dataset: Open Web Text

Neuron 2601 in Layer 4

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: 2.3088. Min Range: -2.3088

Max Act: 2.3088. Min Act: -0.0925

Data Index: 4720291 (Open Web Text)

Max Activating Token Index: 834

Text #1

Max Range: 2.3088. Min Range: -2.3088

Max Act: 2.2892. Min Act: -0.1591

Data Index: 2262040 (Open Web Text)

Max Activating Token Index: 775

Text #2

Max Range: 2.3088. Min Range: -2.3088

Max Act: 2.2984. Min Act: -0.1231

Data Index: 2858918 (Open Web Text)

Max Activating Token Index: 289

Text #3

Max Range: 2.3088. Min Range: -2.3088

Max Act: 2.2974. Min Act: -0.1299

Data Index: 910832 (Open Web Text)

Max Activating Token Index: 738

Text #4

Max Range: 2.3088. Min Range: -2.3088

Max Act: 2.2858. Min Act: -0.1524

Data Index: 4249920 (Open Web Text)

Max Activating Token Index: 578

Text #5

Max Range: 2.3088. Min Range: -2.3088

Max Act: 2.2663. Min Act: -0.1619

Data Index: 2354495 (Open Web Text)

Max Activating Token Index: 924

Text #6

Max Range: 2.3088. Min Range: -2.3088

Max Act: 2.2665. Min Act: -0.1473

Data Index: 6023188 (Open Web Text)

Max Activating Token Index: 637

Text #7

Max Range: 2.3088. Min Range: -2.3088

Max Act: 2.2500. Min Act: -0.1603

Data Index: 8084673 (Open Web Text)

Max Activating Token Index: 1010

Text #8

Max Range: 2.3088. Min Range: -2.3088

Max Act: 2.2712. Min Act: -0.1616

Data Index: 8151375 (Open Web Text)

Max Activating Token Index: 60

Text #9

Max Range: 2.3088. Min Range: -2.3088

Max Act: 2.2719. Min Act: -0.1525

Data Index: 667751 (Open Web Text)

Max Activating Token Index: 767

Text #10

Max Range: 2.3088. Min Range: -2.3088

Max Act: 2.2499. Min Act: -0.1416

Data Index: 5910888 (Open Web Text)

Max Activating Token Index: 403

Text #11

Max Range: 2.3088. Min Range: -2.3088

Max Act: 2.2470. Min Act: -0.1107

Data Index: 667752 (Open Web Text)

Max Activating Token Index: 548

Text #12

Max Range: 2.3088. Min Range: -2.3088

Max Act: 2.2350. Min Act: -0.1523

Data Index: 2537541 (Open Web Text)

Max Activating Token Index: 954

Text #13

Max Range: 2.3088. Min Range: -2.3088

Max Act: 2.2157. Min Act: -0.1533

Data Index: 7006689 (Open Web Text)

Max Activating Token Index: 780

Text #14

Max Range: 2.3088. Min Range: -2.3088

Max Act: 2.2598. Min Act: -0.1344

Data Index: 667750 (Open Web Text)

Max Activating Token Index: 738

Text #15

Max Range: 2.3088. Min Range: -2.3088

Max Act: 2.2477. Min Act: -0.1650

Data Index: 7406126 (Open Web Text)

Max Activating Token Index: 492

Text #16

Max Range: 2.3088. Min Range: -2.3088

Max Act: 2.2516. Min Act: -0.1678

Data Index: 808366 (Open Web Text)

Max Activating Token Index: 995

Text #17

Max Range: 2.3088. Min Range: -2.3088

Max Act: 2.2214. Min Act: -0.1079

Data Index: 3992559 (Open Web Text)

Max Activating Token Index: 405

Text #18

Max Range: 2.3088. Min Range: -2.3088

Max Act: 2.2401. Min Act: -0.1083

Data Index: 7710951 (Open Web Text)

Max Activating Token Index: 972

Text #19

Max Range: 2.3088. Min Range: -2.3088

Max Act: 2.2134. Min Act: -0.1606

Data Index: 667765 (Open Web Text)

Max Activating Token Index: 987