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

Dataset: Open Web Text

Neuron 2406 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: 3.5366. Min Range: -3.5366

Max Act: 3.5366. Min Act: -0.1700

Data Index: 8079363 (Open Web Text)

Max Activating Token Index: 11

Text #1

Max Range: 3.5366. Min Range: -3.5366

Max Act: 3.4260. Min Act: -0.1700

Data Index: 1097754 (Open Web Text)

Max Activating Token Index: 54

Text #2

Max Range: 3.5366. Min Range: -3.5366

Max Act: 3.3726. Min Act: -0.1700

Data Index: 3594416 (Open Web Text)

Max Activating Token Index: 20

Text #3

Max Range: 3.5366. Min Range: -3.5366

Max Act: 3.3291. Min Act: -0.1700

Data Index: 4520396 (Open Web Text)

Max Activating Token Index: 267

Text #4

Max Range: 3.5366. Min Range: -3.5366

Max Act: 3.3217. Min Act: -0.1700

Data Index: 6474497 (Open Web Text)

Max Activating Token Index: 46

Text #5

Max Range: 3.5366. Min Range: -3.5366

Max Act: 3.3229. Min Act: -0.1700

Data Index: 4989410 (Open Web Text)

Max Activating Token Index: 72

Text #6

Max Range: 3.5366. Min Range: -3.5366

Max Act: 3.3086. Min Act: -0.1700

Data Index: 2645430 (Open Web Text)

Max Activating Token Index: 69

Text #7

Max Range: 3.5366. Min Range: -3.5366

Max Act: 3.3059. Min Act: -0.1700

Data Index: 8241583 (Open Web Text)

Max Activating Token Index: 48

Text #8

Max Range: 3.5366. Min Range: -3.5366

Max Act: 3.2950. Min Act: -0.1700

Data Index: 443091 (Open Web Text)

Max Activating Token Index: 45

Text #9

Max Range: 3.5366. Min Range: -3.5366

Max Act: 3.2690. Min Act: -0.1700

Data Index: 5542745 (Open Web Text)

Max Activating Token Index: 50

Text #10

Max Range: 3.5366. Min Range: -3.5366

Max Act: 3.2577. Min Act: -0.1700

Data Index: 2762399 (Open Web Text)

Max Activating Token Index: 11

Text #11

Max Range: 3.5366. Min Range: -3.5366

Max Act: 3.2628. Min Act: -0.1700

Data Index: 2946678 (Open Web Text)

Max Activating Token Index: 386

Text #12

Max Range: 3.5366. Min Range: -3.5366

Max Act: 3.2422. Min Act: -0.1698

Data Index: 2187827 (Open Web Text)

Max Activating Token Index: 130

Text #13

Max Range: 3.5366. Min Range: -3.5366

Max Act: 3.2237. Min Act: -0.1699

Data Index: 4963965 (Open Web Text)

Max Activating Token Index: 50

Text #14

Max Range: 3.5366. Min Range: -3.5366

Max Act: 3.2299. Min Act: -0.1700

Data Index: 5845201 (Open Web Text)

Max Activating Token Index: 642

Text #15

Max Range: 3.5366. Min Range: -3.5366

Max Act: 3.2286. Min Act: -0.1700

Data Index: 4229034 (Open Web Text)

Max Activating Token Index: 86

Text #16

Max Range: 3.5366. Min Range: -3.5366

Max Act: 3.2412. Min Act: -0.1700

Data Index: 7106015 (Open Web Text)

Max Activating Token Index: 480

Text #17

Max Range: 3.5366. Min Range: -3.5366

Max Act: 3.2081. Min Act: -0.1700

Data Index: 4966553 (Open Web Text)

Max Activating Token Index: 641

Text #18

Max Range: 3.5366. Min Range: -3.5366

Max Act: 3.2191. Min Act: -0.1700

Data Index: 2228641 (Open Web Text)

Max Activating Token Index: 840

Text #19

Max Range: 3.5366. Min Range: -3.5366

Max Act: 3.1949. Min Act: -0.1700

Data Index: 4515324 (Open Web Text)

Max Activating Token Index: 58