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

Dataset: Open Web Text

Neuron 1801 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: 3.0395. Min Range: -3.0395

Max Act: 3.0395. Min Act: -0.1700

Data Index: 86970 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 3.0395. Min Range: -3.0395

Max Act: 2.8977. Min Act: -0.1700

Data Index: 3156400 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 3.0395. Min Range: -3.0395

Max Act: 2.9339. Min Act: -0.1700

Data Index: 1276641 (Open Web Text)

Max Activating Token Index: 421

Text #3

Max Range: 3.0395. Min Range: -3.0395

Max Act: 2.8353. Min Act: -0.1700

Data Index: 8388725 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 3.0395. Min Range: -3.0395

Max Act: 2.7848. Min Act: -0.1700

Data Index: 1276640 (Open Web Text)

Max Activating Token Index: 751

Text #5

Max Range: 3.0395. Min Range: -3.0395

Max Act: 2.8333. Min Act: -0.1700

Data Index: 6254003 (Open Web Text)

Max Activating Token Index: 341

Text #6

Max Range: 3.0395. Min Range: -3.0395

Max Act: 2.7569. Min Act: -0.1700

Data Index: 5227065 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 3.0395. Min Range: -3.0395

Max Act: 2.7346. Min Act: -0.1700

Data Index: 10069 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 3.0395. Min Range: -3.0395

Max Act: 2.7179. Min Act: -0.1700

Data Index: 8233248 (Open Web Text)

Max Activating Token Index: 675

Text #9

Max Range: 3.0395. Min Range: -3.0395

Max Act: 2.7413. Min Act: -0.1700

Data Index: 1276639 (Open Web Text)

Max Activating Token Index: 389

Text #10

Max Range: 3.0395. Min Range: -3.0395

Max Act: 2.7143. Min Act: -0.1700

Data Index: 5740407 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 3.0395. Min Range: -3.0395

Max Act: 2.7207. Min Act: -0.1700

Data Index: 3195302 (Open Web Text)

Max Activating Token Index: 655

Text #12

Max Range: 3.0395. Min Range: -3.0395

Max Act: 2.6950. Min Act: -0.1700

Data Index: 5966339 (Open Web Text)

Max Activating Token Index: 1004

Text #13

Max Range: 3.0395. Min Range: -3.0395

Max Act: 2.6797. Min Act: -0.1700

Data Index: 1885445 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 3.0395. Min Range: -3.0395

Max Act: 2.6645. Min Act: -0.1700

Data Index: 8716586 (Open Web Text)

Max Activating Token Index: 134

Text #15

Max Range: 3.0395. Min Range: -3.0395

Max Act: 2.6574. Min Act: -0.1700

Data Index: 974106 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 3.0395. Min Range: -3.0395

Max Act: 2.6420. Min Act: -0.1700

Data Index: 3320768 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 3.0395. Min Range: -3.0395

Max Act: 2.6351. Min Act: -0.1700

Data Index: 6644252 (Open Web Text)

Max Activating Token Index: 265

Text #18

Max Range: 3.0395. Min Range: -3.0395

Max Act: 2.6443. Min Act: -0.1700

Data Index: 3499597 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 3.0395. Min Range: -3.0395

Max Act: 2.6614. Min Act: -0.1700

Data Index: 7698292 (Open Web Text)

Max Activating Token Index: 1023