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

Dataset: Open Web Text

Neuron 845 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: 4.4333. Min Range: -4.4333

Max Act: 4.4333. Min Act: -0.1700

Data Index: 7603084 (Open Web Text)

Max Activating Token Index: 35

Text #1

Max Range: 4.4333. Min Range: -4.4333

Max Act: 4.4037. Min Act: -0.1700

Data Index: 6374272 (Open Web Text)

Max Activating Token Index: 461

Text #2

Max Range: 4.4333. Min Range: -4.4333

Max Act: 4.3585. Min Act: -0.1700

Data Index: 507773 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 4.4333. Min Range: -4.4333

Max Act: 4.3479. Min Act: -0.1700

Data Index: 4192126 (Open Web Text)

Max Activating Token Index: 27

Text #4

Max Range: 4.4333. Min Range: -4.4333

Max Act: 4.2985. Min Act: -0.1700

Data Index: 1325561 (Open Web Text)

Max Activating Token Index: 86

Text #5

Max Range: 4.4333. Min Range: -4.4333

Max Act: 4.2803. Min Act: -0.1700

Data Index: 3614387 (Open Web Text)

Max Activating Token Index: 31

Text #6

Max Range: 4.4333. Min Range: -4.4333

Max Act: 4.3054. Min Act: -0.1700

Data Index: 254385 (Open Web Text)

Max Activating Token Index: 35

Text #7

Max Range: 4.4333. Min Range: -4.4333

Max Act: 4.2825. Min Act: -0.1700

Data Index: 3938827 (Open Web Text)

Max Activating Token Index: 450

Text #8

Max Range: 4.4333. Min Range: -4.4333

Max Act: 4.2658. Min Act: -0.1700

Data Index: 1833522 (Open Web Text)

Max Activating Token Index: 677

Text #9

Max Range: 4.4333. Min Range: -4.4333

Max Act: 4.2370. Min Act: -0.1700

Data Index: 1901080 (Open Web Text)

Max Activating Token Index: 12

Text #10

Max Range: 4.4333. Min Range: -4.4333

Max Act: 4.2516. Min Act: -0.1700

Data Index: 3938826 (Open Web Text)

Max Activating Token Index: 624

Text #11

Max Range: 4.4333. Min Range: -4.4333

Max Act: 4.2371. Min Act: -0.1700

Data Index: 7855401 (Open Web Text)

Max Activating Token Index: 939

Text #12

Max Range: 4.4333. Min Range: -4.4333

Max Act: 4.2095. Min Act: -0.1700

Data Index: 3938828 (Open Web Text)

Max Activating Token Index: 282

Text #13

Max Range: 4.4333. Min Range: -4.4333

Max Act: 4.2066. Min Act: -0.1700

Data Index: 8291517 (Open Web Text)

Max Activating Token Index: 637

Text #14

Max Range: 4.4333. Min Range: -4.4333

Max Act: 4.1927. Min Act: -0.1700

Data Index: 5054247 (Open Web Text)

Max Activating Token Index: 55

Text #15

Max Range: 4.4333. Min Range: -4.4333

Max Act: 4.2147. Min Act: -0.1700

Data Index: 3204089 (Open Web Text)

Max Activating Token Index: 20

Text #16

Max Range: 4.4333. Min Range: -4.4333

Max Act: 4.1739. Min Act: -0.1700

Data Index: 2780100 (Open Web Text)

Max Activating Token Index: 415

Text #17

Max Range: 4.4333. Min Range: -4.4333

Max Act: 4.1699. Min Act: -0.1700

Data Index: 1376986 (Open Web Text)

Max Activating Token Index: 39

Text #18

Max Range: 4.4333. Min Range: -4.4333

Max Act: 4.1683. Min Act: -0.1700

Data Index: 108536 (Open Web Text)

Max Activating Token Index: 62

Text #19

Max Range: 4.4333. Min Range: -4.4333

Max Act: 4.1511. Min Act: -0.1700

Data Index: 352968 (Open Web Text)

Max Activating Token Index: 12