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

Dataset: Open Web Text

Neuron 1106 in Layer 5

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: 3.4796. Min Range: -3.4796

Max Act: 3.4796. Min Act: -0.1700

Data Index: 189498 (Open Web Text)

Max Activating Token Index: 496

Text #1

Max Range: 3.4796. Min Range: -3.4796

Max Act: 3.4750. Min Act: -0.1700

Data Index: 6818108 (Open Web Text)

Max Activating Token Index: 18

Text #2

Max Range: 3.4796. Min Range: -3.4796

Max Act: 3.3556. Min Act: -0.1700

Data Index: 5024179 (Open Web Text)

Max Activating Token Index: 807

Text #3

Max Range: 3.4796. Min Range: -3.4796

Max Act: 3.3654. Min Act: -0.1700

Data Index: 2907096 (Open Web Text)

Max Activating Token Index: 537

Text #4

Max Range: 3.4796. Min Range: -3.4796

Max Act: 3.3397. Min Act: -0.1700

Data Index: 7120733 (Open Web Text)

Max Activating Token Index: 111

Text #5

Max Range: 3.4796. Min Range: -3.4796

Max Act: 3.3452. Min Act: -0.1700

Data Index: 4227972 (Open Web Text)

Max Activating Token Index: 56

Text #6

Max Range: 3.4796. Min Range: -3.4796

Max Act: 3.3311. Min Act: -0.1700

Data Index: 5902921 (Open Web Text)

Max Activating Token Index: 296

Text #7

Max Range: 3.4796. Min Range: -3.4796

Max Act: 3.3247. Min Act: -0.1700

Data Index: 5033967 (Open Web Text)

Max Activating Token Index: 413

Text #8

Max Range: 3.4796. Min Range: -3.4796

Max Act: 3.3062. Min Act: -0.1700

Data Index: 1490458 (Open Web Text)

Max Activating Token Index: 751

Text #9

Max Range: 3.4796. Min Range: -3.4796

Max Act: 3.3076. Min Act: -0.1700

Data Index: 8723142 (Open Web Text)

Max Activating Token Index: 161

Text #10

Max Range: 3.4796. Min Range: -3.4796

Max Act: 3.3097. Min Act: -0.1700

Data Index: 2141445 (Open Web Text)

Max Activating Token Index: 81

Text #11

Max Range: 3.4796. Min Range: -3.4796

Max Act: 3.3077. Min Act: -0.1700

Data Index: 2082098 (Open Web Text)

Max Activating Token Index: 682

Text #12

Max Range: 3.4796. Min Range: -3.4796

Max Act: 3.3246. Min Act: -0.1700

Data Index: 1985023 (Open Web Text)

Max Activating Token Index: 956

Text #13

Max Range: 3.4796. Min Range: -3.4796

Max Act: 3.2895. Min Act: -0.1700

Data Index: 1490494 (Open Web Text)

Max Activating Token Index: 404

Text #14

Max Range: 3.4796. Min Range: -3.4796

Max Act: 3.3031. Min Act: -0.1700

Data Index: 888748 (Open Web Text)

Max Activating Token Index: 935

Text #15

Max Range: 3.4796. Min Range: -3.4796

Max Act: 3.2933. Min Act: -0.1700

Data Index: 285304 (Open Web Text)

Max Activating Token Index: 54

Text #16

Max Range: 3.4796. Min Range: -3.4796

Max Act: 3.2894. Min Act: -0.1700

Data Index: 8237227 (Open Web Text)

Max Activating Token Index: 426

Text #17

Max Range: 3.4796. Min Range: -3.4796

Max Act: 3.2828. Min Act: -0.1700

Data Index: 3881395 (Open Web Text)

Max Activating Token Index: 363

Text #18

Max Range: 3.4796. Min Range: -3.4796

Max Act: 3.2718. Min Act: -0.1700

Data Index: 1520880 (Open Web Text)

Max Activating Token Index: 233

Text #19

Max Range: 3.4796. Min Range: -3.4796

Max Act: 3.2755. Min Act: -0.1700

Data Index: 480639 (Open Web Text)

Max Activating Token Index: 199