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

Dataset: Open Web Text

Neuron 1436 in Layer 3

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: 3.4603. Min Range: -3.4603

Max Act: 3.4603. Min Act: -0.1700

Data Index: 674164 (Open Web Text)

Max Activating Token Index: 186

Text #1

Max Range: 3.4603. Min Range: -3.4603

Max Act: 3.4307. Min Act: -0.1700

Data Index: 6131529 (Open Web Text)

Max Activating Token Index: 290

Text #2

Max Range: 3.4603. Min Range: -3.4603

Max Act: 3.4140. Min Act: -0.1700

Data Index: 4716369 (Open Web Text)

Max Activating Token Index: 693

Text #3

Max Range: 3.4603. Min Range: -3.4603

Max Act: 3.3751. Min Act: -0.1700

Data Index: 1755000 (Open Web Text)

Max Activating Token Index: 488

Text #4

Max Range: 3.4603. Min Range: -3.4603

Max Act: 3.3625. Min Act: -0.1700

Data Index: 1947586 (Open Web Text)

Max Activating Token Index: 931

Text #5

Max Range: 3.4603. Min Range: -3.4603

Max Act: 3.3734. Min Act: -0.1700

Data Index: 7733614 (Open Web Text)

Max Activating Token Index: 195

Text #6

Max Range: 3.4603. Min Range: -3.4603

Max Act: 3.3648. Min Act: -0.1700

Data Index: 2599019 (Open Web Text)

Max Activating Token Index: 509

Text #7

Max Range: 3.4603. Min Range: -3.4603

Max Act: 3.3653. Min Act: -0.1700

Data Index: 5545697 (Open Web Text)

Max Activating Token Index: 11

Text #8

Max Range: 3.4603. Min Range: -3.4603

Max Act: 3.3876. Min Act: -0.1700

Data Index: 6642081 (Open Web Text)

Max Activating Token Index: 983

Text #9

Max Range: 3.4603. Min Range: -3.4603

Max Act: 3.3298. Min Act: -0.1700

Data Index: 5381925 (Open Web Text)

Max Activating Token Index: 26

Text #10

Max Range: 3.4603. Min Range: -3.4603

Max Act: 3.3528. Min Act: -0.1700

Data Index: 8064963 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 3.4603. Min Range: -3.4603

Max Act: 3.3528. Min Act: -0.1700

Data Index: 1562162 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.4603. Min Range: -3.4603

Max Act: 3.3171. Min Act: -0.1700

Data Index: 8519273 (Open Web Text)

Max Activating Token Index: 65

Text #13

Max Range: 3.4603. Min Range: -3.4603

Max Act: 3.3302. Min Act: -0.1700

Data Index: 5921767 (Open Web Text)

Max Activating Token Index: 647

Text #14

Max Range: 3.4603. Min Range: -3.4603

Max Act: 3.3223. Min Act: -0.1700

Data Index: 704043 (Open Web Text)

Max Activating Token Index: 278

Text #15

Max Range: 3.4603. Min Range: -3.4603

Max Act: 3.3247. Min Act: -0.1700

Data Index: 7062237 (Open Web Text)

Max Activating Token Index: 841

Text #16

Max Range: 3.4603. Min Range: -3.4603

Max Act: 3.3113. Min Act: -0.1700

Data Index: 3263522 (Open Web Text)

Max Activating Token Index: 108

Text #17

Max Range: 3.4603. Min Range: -3.4603

Max Act: 3.2985. Min Act: -0.1700

Data Index: 6642082 (Open Web Text)

Max Activating Token Index: 96

Text #18

Max Range: 3.4603. Min Range: -3.4603

Max Act: 3.3086. Min Act: -0.1700

Data Index: 8106261 (Open Web Text)

Max Activating Token Index: 828

Text #19

Max Range: 3.4603. Min Range: -3.4603

Max Act: 3.3206. Min Act: -0.1700

Data Index: 7298285 (Open Web Text)

Max Activating Token Index: 693