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

Dataset: Open Web Text

Neuron 820 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: 1.0659. Min Range: -1.0659

Max Act: 1.0591. Min Act: -0.0561

Data Index: 8233844 (Open Web Text)

Max Activating Token Index: 67

Text #1

Max Range: 1.0659. Min Range: -1.0659

Max Act: 1.0644. Min Act: -0.0479

Data Index: 2087900 (Open Web Text)

Max Activating Token Index: 74

Text #2

Max Range: 1.0659. Min Range: -1.0659

Max Act: 1.0619. Min Act: -0.0921

Data Index: 4025517 (Open Web Text)

Max Activating Token Index: 60

Text #3

Max Range: 1.0659. Min Range: -1.0659

Max Act: 1.0659. Min Act: -0.0835

Data Index: 2239241 (Open Web Text)

Max Activating Token Index: 66

Text #4

Max Range: 1.0659. Min Range: -1.0659

Max Act: 1.0602. Min Act: -0.0621

Data Index: 4356748 (Open Web Text)

Max Activating Token Index: 75

Text #5

Max Range: 1.0659. Min Range: -1.0659

Max Act: 1.0567. Min Act: -0.0722

Data Index: 3668734 (Open Web Text)

Max Activating Token Index: 96

Text #6

Max Range: 1.0659. Min Range: -1.0659

Max Act: 1.0571. Min Act: -0.0628

Data Index: 5710478 (Open Web Text)

Max Activating Token Index: 63

Text #7

Max Range: 1.0659. Min Range: -1.0659

Max Act: 1.0475. Min Act: -0.0431

Data Index: 4121996 (Open Web Text)

Max Activating Token Index: 885

Text #8

Max Range: 1.0659. Min Range: -1.0659

Max Act: 1.0484. Min Act: -0.0395

Data Index: 5733142 (Open Web Text)

Max Activating Token Index: 55

Text #9

Max Range: 1.0659. Min Range: -1.0659

Max Act: 1.0383. Min Act: -0.0556

Data Index: 1515107 (Open Web Text)

Max Activating Token Index: 64

Text #10

Max Range: 1.0659. Min Range: -1.0659

Max Act: 1.0330. Min Act: -0.0397

Data Index: 6324904 (Open Web Text)

Max Activating Token Index: 65

Text #11

Max Range: 1.0659. Min Range: -1.0659

Max Act: 1.0401. Min Act: -0.0433

Data Index: 7338310 (Open Web Text)

Max Activating Token Index: 890

Text #12

Max Range: 1.0659. Min Range: -1.0659

Max Act: 1.0220. Min Act: -0.0862

Data Index: 8696266 (Open Web Text)

Max Activating Token Index: 60

Text #13

Max Range: 1.0659. Min Range: -1.0659

Max Act: 1.0298. Min Act: -0.0127

Data Index: 2894349 (Open Web Text)

Max Activating Token Index: 79

Text #14

Max Range: 1.0659. Min Range: -1.0659

Max Act: 1.0294. Min Act: -0.0827

Data Index: 8639293 (Open Web Text)

Max Activating Token Index: 68

Text #15

Max Range: 1.0659. Min Range: -1.0659

Max Act: 1.0241. Min Act: -0.0319

Data Index: 2867949 (Open Web Text)

Max Activating Token Index: 74

Text #16

Max Range: 1.0659. Min Range: -1.0659

Max Act: 1.0276. Min Act: -0.0624

Data Index: 1204671 (Open Web Text)

Max Activating Token Index: 68

Text #17

Max Range: 1.0659. Min Range: -1.0659

Max Act: 1.0297. Min Act: -0.0608

Data Index: 8244354 (Open Web Text)

Max Activating Token Index: 63

Text #18

Max Range: 1.0659. Min Range: -1.0659

Max Act: 1.0302. Min Act: -0.0431

Data Index: 6758587 (Open Web Text)

Max Activating Token Index: 99

Text #19

Max Range: 1.0659. Min Range: -1.0659

Max Act: 1.0171. Min Act: -0.0452

Data Index: 2996919 (Open Web Text)

Max Activating Token Index: 70