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

Dataset: Open Web Text

Neuron 487 in Layer 4

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: 4.5004. Min Range: -4.5004

Max Act: 4.5004. Min Act: -0.1700

Data Index: 5261461 (Open Web Text)

Max Activating Token Index: 669

Text #1

Max Range: 4.5004. Min Range: -4.5004

Max Act: 4.3461. Min Act: -0.1700

Data Index: 1706543 (Open Web Text)

Max Activating Token Index: 845

Text #2

Max Range: 4.5004. Min Range: -4.5004

Max Act: 4.3449. Min Act: -0.1700

Data Index: 3279225 (Open Web Text)

Max Activating Token Index: 769

Text #3

Max Range: 4.5004. Min Range: -4.5004

Max Act: 4.3017. Min Act: -0.1700

Data Index: 567840 (Open Web Text)

Max Activating Token Index: 47

Text #4

Max Range: 4.5004. Min Range: -4.5004

Max Act: 4.2762. Min Act: -0.1700

Data Index: 5669343 (Open Web Text)

Max Activating Token Index: 321

Text #5

Max Range: 4.5004. Min Range: -4.5004

Max Act: 4.2444. Min Act: -0.1700

Data Index: 5994342 (Open Web Text)

Max Activating Token Index: 614

Text #6

Max Range: 4.5004. Min Range: -4.5004

Max Act: 4.2884. Min Act: -0.1700

Data Index: 3001072 (Open Web Text)

Max Activating Token Index: 153

Text #7

Max Range: 4.5004. Min Range: -4.5004

Max Act: 4.2526. Min Act: -0.1700

Data Index: 1288526 (Open Web Text)

Max Activating Token Index: 13

Text #8

Max Range: 4.5004. Min Range: -4.5004

Max Act: 4.2898. Min Act: -0.1700

Data Index: 5650314 (Open Web Text)

Max Activating Token Index: 183

Text #9

Max Range: 4.5004. Min Range: -4.5004

Max Act: 4.2167. Min Act: -0.1700

Data Index: 1040394 (Open Web Text)

Max Activating Token Index: 565

Text #10

Max Range: 4.5004. Min Range: -4.5004

Max Act: 4.2088. Min Act: -0.1700

Data Index: 3285437 (Open Web Text)

Max Activating Token Index: 549

Text #11

Max Range: 4.5004. Min Range: -4.5004

Max Act: 4.2092. Min Act: -0.1700

Data Index: 8816247 (Open Web Text)

Max Activating Token Index: 599

Text #12

Max Range: 4.5004. Min Range: -4.5004

Max Act: 4.2105. Min Act: -0.1700

Data Index: 8728886 (Open Web Text)

Max Activating Token Index: 196

Text #13

Max Range: 4.5004. Min Range: -4.5004

Max Act: 4.1857. Min Act: -0.1700

Data Index: 260035 (Open Web Text)

Max Activating Token Index: 159

Text #14

Max Range: 4.5004. Min Range: -4.5004

Max Act: 4.2331. Min Act: -0.1700

Data Index: 1561082 (Open Web Text)

Max Activating Token Index: 746

Text #15

Max Range: 4.5004. Min Range: -4.5004

Max Act: 4.1378. Min Act: -0.1700

Data Index: 1679411 (Open Web Text)

Max Activating Token Index: 981

Text #16

Max Range: 4.5004. Min Range: -4.5004

Max Act: 4.1193. Min Act: -0.1700

Data Index: 4864489 (Open Web Text)

Max Activating Token Index: 904

Text #17

Max Range: 4.5004. Min Range: -4.5004

Max Act: 4.1738. Min Act: -0.1700

Data Index: 7457707 (Open Web Text)

Max Activating Token Index: 720

Text #18

Max Range: 4.5004. Min Range: -4.5004

Max Act: 4.1575. Min Act: -0.1700

Data Index: 4321099 (Open Web Text)

Max Activating Token Index: 315

Text #19

Max Range: 4.5004. Min Range: -4.5004

Max Act: 4.1391. Min Act: -0.1700

Data Index: 3736948 (Open Web Text)

Max Activating Token Index: 392