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

Dataset: Open Web Text

Neuron 1360 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: 1.9282. Min Range: -1.9282

Max Act: 1.9282. Min Act: -0.1700

Data Index: 6884302 (Open Web Text)

Max Activating Token Index: 44

Text #1

Max Range: 1.9282. Min Range: -1.9282

Max Act: 1.9203. Min Act: -0.1700

Data Index: 1550100 (Open Web Text)

Max Activating Token Index: 120

Text #2

Max Range: 1.9282. Min Range: -1.9282

Max Act: 1.9030. Min Act: -0.1699

Data Index: 7426771 (Open Web Text)

Max Activating Token Index: 333

Text #3

Max Range: 1.9282. Min Range: -1.9282

Max Act: 1.8828. Min Act: -0.1700

Data Index: 7178343 (Open Web Text)

Max Activating Token Index: 96

Text #4

Max Range: 1.9282. Min Range: -1.9282

Max Act: 1.8938. Min Act: -0.1700

Data Index: 3594365 (Open Web Text)

Max Activating Token Index: 132

Text #5

Max Range: 1.9282. Min Range: -1.9282

Max Act: 1.8805. Min Act: -0.1700

Data Index: 5363605 (Open Web Text)

Max Activating Token Index: 51

Text #6

Max Range: 1.9282. Min Range: -1.9282

Max Act: 1.8828. Min Act: -0.1700

Data Index: 6293363 (Open Web Text)

Max Activating Token Index: 63

Text #7

Max Range: 1.9282. Min Range: -1.9282

Max Act: 1.8737. Min Act: -0.1697

Data Index: 4934583 (Open Web Text)

Max Activating Token Index: 92

Text #8

Max Range: 1.9282. Min Range: -1.9282

Max Act: 1.8781. Min Act: -0.1698

Data Index: 3681056 (Open Web Text)

Max Activating Token Index: 85

Text #9

Max Range: 1.9282. Min Range: -1.9282

Max Act: 1.8775. Min Act: -0.1700

Data Index: 1790377 (Open Web Text)

Max Activating Token Index: 141

Text #10

Max Range: 1.9282. Min Range: -1.9282

Max Act: 1.8713. Min Act: -0.1700

Data Index: 1350047 (Open Web Text)

Max Activating Token Index: 101

Text #11

Max Range: 1.9282. Min Range: -1.9282

Max Act: 1.8537. Min Act: -0.1700

Data Index: 6918724 (Open Web Text)

Max Activating Token Index: 100

Text #12

Max Range: 1.9282. Min Range: -1.9282

Max Act: 1.8443. Min Act: -0.1700

Data Index: 6843968 (Open Web Text)

Max Activating Token Index: 93

Text #13

Max Range: 1.9282. Min Range: -1.9282

Max Act: 1.8524. Min Act: -0.1700

Data Index: 5023579 (Open Web Text)

Max Activating Token Index: 48

Text #14

Max Range: 1.9282. Min Range: -1.9282

Max Act: 1.8460. Min Act: -0.1699

Data Index: 3989866 (Open Web Text)

Max Activating Token Index: 646

Text #15

Max Range: 1.9282. Min Range: -1.9282

Max Act: 1.8426. Min Act: -0.1700

Data Index: 3953611 (Open Web Text)

Max Activating Token Index: 87

Text #16

Max Range: 1.9282. Min Range: -1.9282

Max Act: 1.8422. Min Act: -0.1700

Data Index: 2386259 (Open Web Text)

Max Activating Token Index: 911

Text #17

Max Range: 1.9282. Min Range: -1.9282

Max Act: 1.8447. Min Act: -0.1700

Data Index: 4275824 (Open Web Text)

Max Activating Token Index: 57

Text #18

Max Range: 1.9282. Min Range: -1.9282

Max Act: 1.8475. Min Act: -0.1700

Data Index: 6516956 (Open Web Text)

Max Activating Token Index: 1017

Text #19

Max Range: 1.9282. Min Range: -1.9282

Max Act: 1.8360. Min Act: -0.1689

Data Index: 4250063 (Open Web Text)

Max Activating Token Index: 424