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

Dataset: Open Web Text

Neuron 2214 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: 3.4975. Min Range: -3.4975

Max Act: 3.4975. Min Act: -0.1700

Data Index: 2690896 (Open Web Text)

Max Activating Token Index: 346

Text #1

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.3494. Min Act: -0.1700

Data Index: 5082200 (Open Web Text)

Max Activating Token Index: 905

Text #2

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.2699. Min Act: -0.1700

Data Index: 7021549 (Open Web Text)

Max Activating Token Index: 536

Text #3

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.2713. Min Act: -0.1700

Data Index: 6400543 (Open Web Text)

Max Activating Token Index: 68

Text #4

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.2556. Min Act: -0.1700

Data Index: 8714502 (Open Web Text)

Max Activating Token Index: 657

Text #5

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.2259. Min Act: -0.1700

Data Index: 8821175 (Open Web Text)

Max Activating Token Index: 71

Text #6

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.1963. Min Act: -0.1700

Data Index: 1127476 (Open Web Text)

Max Activating Token Index: 911

Text #7

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.1726. Min Act: -0.1700

Data Index: 4415115 (Open Web Text)

Max Activating Token Index: 78

Text #8

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.1550. Min Act: -0.1700

Data Index: 2803773 (Open Web Text)

Max Activating Token Index: 44

Text #9

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.1594. Min Act: -0.1700

Data Index: 8733745 (Open Web Text)

Max Activating Token Index: 45

Text #10

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.1401. Min Act: -0.1700

Data Index: 5450007 (Open Web Text)

Max Activating Token Index: 41

Text #11

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.1550. Min Act: -0.1700

Data Index: 5343729 (Open Web Text)

Max Activating Token Index: 508

Text #12

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.1515. Min Act: -0.1700

Data Index: 7437352 (Open Web Text)

Max Activating Token Index: 34

Text #13

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.1605. Min Act: -0.1700

Data Index: 6349787 (Open Web Text)

Max Activating Token Index: 89

Text #14

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.1008. Min Act: -0.1700

Data Index: 7293252 (Open Web Text)

Max Activating Token Index: 456

Text #15

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.1370. Min Act: -0.1700

Data Index: 6009935 (Open Web Text)

Max Activating Token Index: 832

Text #16

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.1176. Min Act: -0.1700

Data Index: 4845420 (Open Web Text)

Max Activating Token Index: 11

Text #17

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.1356. Min Act: -0.1700

Data Index: 6335128 (Open Web Text)

Max Activating Token Index: 371

Text #18

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.1203. Min Act: -0.1700

Data Index: 5266619 (Open Web Text)

Max Activating Token Index: 72

Text #19

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.1195. Min Act: -0.1700

Data Index: 7430492 (Open Web Text)

Max Activating Token Index: 926