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

Dataset: Open Web Text

Neuron 2826 in Layer 2

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: 4.3699. Min Range: -4.3699

Max Act: 4.3699. Min Act: -0.1700

Data Index: 1558048 (Open Web Text)

Max Activating Token Index: 655

Text #1

Max Range: 4.3699. Min Range: -4.3699

Max Act: 4.3209. Min Act: -0.1700

Data Index: 4143262 (Open Web Text)

Max Activating Token Index: 882

Text #2

Max Range: 4.3699. Min Range: -4.3699

Max Act: 4.3105. Min Act: -0.1700

Data Index: 2967334 (Open Web Text)

Max Activating Token Index: 710

Text #3

Max Range: 4.3699. Min Range: -4.3699

Max Act: 4.3215. Min Act: -0.1700

Data Index: 976420 (Open Web Text)

Max Activating Token Index: 357

Text #4

Max Range: 4.3699. Min Range: -4.3699

Max Act: 4.3417. Min Act: -0.1700

Data Index: 3616284 (Open Web Text)

Max Activating Token Index: 359

Text #5

Max Range: 4.3699. Min Range: -4.3699

Max Act: 4.3038. Min Act: -0.1700

Data Index: 4567137 (Open Web Text)

Max Activating Token Index: 348

Text #6

Max Range: 4.3699. Min Range: -4.3699

Max Act: 4.3156. Min Act: -0.1700

Data Index: 23963 (Open Web Text)

Max Activating Token Index: 997

Text #7

Max Range: 4.3699. Min Range: -4.3699

Max Act: 4.3250. Min Act: -0.1700

Data Index: 379667 (Open Web Text)

Max Activating Token Index: 973

Text #8

Max Range: 4.3699. Min Range: -4.3699

Max Act: 4.3015. Min Act: -0.1700

Data Index: 4411872 (Open Web Text)

Max Activating Token Index: 464

Text #9

Max Range: 4.3699. Min Range: -4.3699

Max Act: 4.2917. Min Act: -0.1700

Data Index: 2362831 (Open Web Text)

Max Activating Token Index: 840

Text #10

Max Range: 4.3699. Min Range: -4.3699

Max Act: 4.3045. Min Act: -0.1700

Data Index: 2274350 (Open Web Text)

Max Activating Token Index: 215

Text #11

Max Range: 4.3699. Min Range: -4.3699

Max Act: 4.2653. Min Act: -0.1700

Data Index: 2522197 (Open Web Text)

Max Activating Token Index: 390

Text #12

Max Range: 4.3699. Min Range: -4.3699

Max Act: 4.2552. Min Act: -0.1700

Data Index: 4012201 (Open Web Text)

Max Activating Token Index: 170

Text #13

Max Range: 4.3699. Min Range: -4.3699

Max Act: 4.2794. Min Act: -0.1700

Data Index: 7875114 (Open Web Text)

Max Activating Token Index: 655

Text #14

Max Range: 4.3699. Min Range: -4.3699

Max Act: 4.2577. Min Act: -0.1700

Data Index: 383768 (Open Web Text)

Max Activating Token Index: 1003

Text #15

Max Range: 4.3699. Min Range: -4.3699

Max Act: 4.2439. Min Act: -0.1700

Data Index: 5141621 (Open Web Text)

Max Activating Token Index: 923

Text #16

Max Range: 4.3699. Min Range: -4.3699

Max Act: 4.2152. Min Act: -0.1700

Data Index: 7482073 (Open Web Text)

Max Activating Token Index: 970

Text #17

Max Range: 4.3699. Min Range: -4.3699

Max Act: 4.2250. Min Act: -0.1700

Data Index: 4074630 (Open Web Text)

Max Activating Token Index: 782

Text #18

Max Range: 4.3699. Min Range: -4.3699

Max Act: 4.2704. Min Act: -0.1700

Data Index: 5110887 (Open Web Text)

Max Activating Token Index: 544

Text #19

Max Range: 4.3699. Min Range: -4.3699

Max Act: 4.2258. Min Act: -0.1700

Data Index: 939445 (Open Web Text)

Max Activating Token Index: 465