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

Dataset: Open Web Text

Neuron 620 in Layer 0

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: 3.2280. Min Range: -3.2280

Max Act: 3.2280. Min Act: -0.1700

Data Index: 969724 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.2280. Min Range: -3.2280

Max Act: 3.1628. Min Act: -0.1700

Data Index: 7732362 (Open Web Text)

Max Activating Token Index: 608

Text #2

Max Range: 3.2280. Min Range: -3.2280

Max Act: 3.1411. Min Act: -0.1700

Data Index: 6084120 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.2280. Min Range: -3.2280

Max Act: 3.1402. Min Act: -0.1700

Data Index: 7520969 (Open Web Text)

Max Activating Token Index: 411

Text #4

Max Range: 3.2280. Min Range: -3.2280

Max Act: 3.1452. Min Act: -0.1700

Data Index: 961182 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 3.2280. Min Range: -3.2280

Max Act: 3.1286. Min Act: -0.1700

Data Index: 4305142 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 3.2280. Min Range: -3.2280

Max Act: 3.1259. Min Act: -0.1700

Data Index: 7131218 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 3.2280. Min Range: -3.2280

Max Act: 3.0987. Min Act: -0.1700

Data Index: 7782865 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 3.2280. Min Range: -3.2280

Max Act: 3.0945. Min Act: -0.1700

Data Index: 7706074 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 3.2280. Min Range: -3.2280

Max Act: 3.0837. Min Act: -0.1700

Data Index: 3955099 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 3.2280. Min Range: -3.2280

Max Act: 3.0861. Min Act: -0.1700

Data Index: 7592639 (Open Web Text)

Max Activating Token Index: 958

Text #11

Max Range: 3.2280. Min Range: -3.2280

Max Act: 3.0788. Min Act: -0.1700

Data Index: 2920691 (Open Web Text)

Max Activating Token Index: 9

Text #12

Max Range: 3.2280. Min Range: -3.2280

Max Act: 3.0787. Min Act: -0.1700

Data Index: 2442281 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 3.2280. Min Range: -3.2280

Max Act: 3.0835. Min Act: -0.1700

Data Index: 5987684 (Open Web Text)

Max Activating Token Index: 124

Text #14

Max Range: 3.2280. Min Range: -3.2280

Max Act: 3.0730. Min Act: -0.1700

Data Index: 3470611 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 3.2280. Min Range: -3.2280

Max Act: 3.0678. Min Act: -0.1700

Data Index: 6438586 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 3.2280. Min Range: -3.2280

Max Act: 3.0588. Min Act: -0.1700

Data Index: 2808410 (Open Web Text)

Max Activating Token Index: 14

Text #17

Max Range: 3.2280. Min Range: -3.2280

Max Act: 3.0495. Min Act: -0.1700

Data Index: 6485781 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 3.2280. Min Range: -3.2280

Max Act: 3.0403. Min Act: -0.1700

Data Index: 2195570 (Open Web Text)

Max Activating Token Index: 23

Text #19

Max Range: 3.2280. Min Range: -3.2280

Max Act: 3.0426. Min Act: -0.1700

Data Index: 7637714 (Open Web Text)

Max Activating Token Index: 10