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

Dataset: Open Web Text

Neuron 736 in Layer 1

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: 1.6630. Min Range: -1.6630

Max Act: 1.6630. Min Act: -0.1700

Data Index: 6476148 (Open Web Text)

Max Activating Token Index: 887

Text #1

Max Range: 1.6630. Min Range: -1.6630

Max Act: 1.6533. Min Act: -0.1700

Data Index: 6970755 (Open Web Text)

Max Activating Token Index: 53

Text #2

Max Range: 1.6630. Min Range: -1.6630

Max Act: 1.6281. Min Act: -0.1700

Data Index: 5545524 (Open Web Text)

Max Activating Token Index: 249

Text #3

Max Range: 1.6630. Min Range: -1.6630

Max Act: 1.6334. Min Act: -0.1700

Data Index: 5287506 (Open Web Text)

Max Activating Token Index: 110

Text #4

Max Range: 1.6630. Min Range: -1.6630

Max Act: 1.6283. Min Act: -0.1700

Data Index: 4616766 (Open Web Text)

Max Activating Token Index: 430

Text #5

Max Range: 1.6630. Min Range: -1.6630

Max Act: 1.6301. Min Act: -0.1700

Data Index: 4037676 (Open Web Text)

Max Activating Token Index: 558

Text #6

Max Range: 1.6630. Min Range: -1.6630

Max Act: 1.6257. Min Act: -0.1700

Data Index: 6427200 (Open Web Text)

Max Activating Token Index: 401

Text #7

Max Range: 1.6630. Min Range: -1.6630

Max Act: 1.6306. Min Act: -0.1700

Data Index: 4243523 (Open Web Text)

Max Activating Token Index: 220

Text #8

Max Range: 1.6630. Min Range: -1.6630

Max Act: 1.6210. Min Act: -0.1700

Data Index: 3227189 (Open Web Text)

Max Activating Token Index: 53

Text #9

Max Range: 1.6630. Min Range: -1.6630

Max Act: 1.6166. Min Act: -0.1700

Data Index: 3127108 (Open Web Text)

Max Activating Token Index: 887

Text #10

Max Range: 1.6630. Min Range: -1.6630

Max Act: 1.6241. Min Act: -0.1699

Data Index: 42923 (Open Web Text)

Max Activating Token Index: 578

Text #11

Max Range: 1.6630. Min Range: -1.6630

Max Act: 1.6062. Min Act: -0.1700

Data Index: 4047131 (Open Web Text)

Max Activating Token Index: 753

Text #12

Max Range: 1.6630. Min Range: -1.6630

Max Act: 1.6072. Min Act: -0.1700

Data Index: 3039086 (Open Web Text)

Max Activating Token Index: 972

Text #13

Max Range: 1.6630. Min Range: -1.6630

Max Act: 1.6041. Min Act: -0.1700

Data Index: 6739139 (Open Web Text)

Max Activating Token Index: 629

Text #14

Max Range: 1.6630. Min Range: -1.6630

Max Act: 1.6046. Min Act: -0.1699

Data Index: 494307 (Open Web Text)

Max Activating Token Index: 714

Text #15

Max Range: 1.6630. Min Range: -1.6630

Max Act: 1.5873. Min Act: -0.1700

Data Index: 6154251 (Open Web Text)

Max Activating Token Index: 660

Text #16

Max Range: 1.6630. Min Range: -1.6630

Max Act: 1.5917. Min Act: -0.1700

Data Index: 4594107 (Open Web Text)

Max Activating Token Index: 119

Text #17

Max Range: 1.6630. Min Range: -1.6630

Max Act: 1.5986. Min Act: -0.1700

Data Index: 508274 (Open Web Text)

Max Activating Token Index: 620

Text #18

Max Range: 1.6630. Min Range: -1.6630

Max Act: 1.5990. Min Act: -0.1700

Data Index: 4932625 (Open Web Text)

Max Activating Token Index: 13

Text #19

Max Range: 1.6630. Min Range: -1.6630

Max Act: 1.5947. Min Act: -0.1700

Data Index: 3956150 (Open Web Text)

Max Activating Token Index: 390