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

Dataset: Open Web Text

Neuron 374 in Layer 5

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: 3.5031. Min Range: -3.5031

Max Act: 3.4915. Min Act: -0.1700

Data Index: 2987255 (Open Web Text)

Max Activating Token Index: 164

Text #1

Max Range: 3.5031. Min Range: -3.5031

Max Act: 3.5031. Min Act: -0.1700

Data Index: 7265401 (Open Web Text)

Max Activating Token Index: 966

Text #2

Max Range: 3.5031. Min Range: -3.5031

Max Act: 3.4765. Min Act: -0.1700

Data Index: 6358204 (Open Web Text)

Max Activating Token Index: 195

Text #3

Max Range: 3.5031. Min Range: -3.5031

Max Act: 3.4576. Min Act: -0.1700

Data Index: 8783619 (Open Web Text)

Max Activating Token Index: 840

Text #4

Max Range: 3.5031. Min Range: -3.5031

Max Act: 3.4037. Min Act: -0.1700

Data Index: 6016743 (Open Web Text)

Max Activating Token Index: 487

Text #5

Max Range: 3.5031. Min Range: -3.5031

Max Act: 3.3859. Min Act: -0.1700

Data Index: 1100746 (Open Web Text)

Max Activating Token Index: 699

Text #6

Max Range: 3.5031. Min Range: -3.5031

Max Act: 3.4200. Min Act: -0.1700

Data Index: 5673741 (Open Web Text)

Max Activating Token Index: 768

Text #7

Max Range: 3.5031. Min Range: -3.5031

Max Act: 3.3814. Min Act: -0.1700

Data Index: 430095 (Open Web Text)

Max Activating Token Index: 383

Text #8

Max Range: 3.5031. Min Range: -3.5031

Max Act: 3.3621. Min Act: -0.1700

Data Index: 4743578 (Open Web Text)

Max Activating Token Index: 156

Text #9

Max Range: 3.5031. Min Range: -3.5031

Max Act: 3.3686. Min Act: -0.1700

Data Index: 7596267 (Open Web Text)

Max Activating Token Index: 536

Text #10

Max Range: 3.5031. Min Range: -3.5031

Max Act: 3.3249. Min Act: -0.1700

Data Index: 5188296 (Open Web Text)

Max Activating Token Index: 332

Text #11

Max Range: 3.5031. Min Range: -3.5031

Max Act: 3.3330. Min Act: -0.1700

Data Index: 716822 (Open Web Text)

Max Activating Token Index: 476

Text #12

Max Range: 3.5031. Min Range: -3.5031

Max Act: 3.3524. Min Act: -0.1700

Data Index: 2050557 (Open Web Text)

Max Activating Token Index: 895

Text #13

Max Range: 3.5031. Min Range: -3.5031

Max Act: 3.3184. Min Act: -0.1700

Data Index: 390075 (Open Web Text)

Max Activating Token Index: 678

Text #14

Max Range: 3.5031. Min Range: -3.5031

Max Act: 3.3308. Min Act: -0.1700

Data Index: 5713736 (Open Web Text)

Max Activating Token Index: 787

Text #15

Max Range: 3.5031. Min Range: -3.5031

Max Act: 3.2866. Min Act: -0.1700

Data Index: 3096503 (Open Web Text)

Max Activating Token Index: 719

Text #16

Max Range: 3.5031. Min Range: -3.5031

Max Act: 3.3220. Min Act: -0.1700

Data Index: 2545053 (Open Web Text)

Max Activating Token Index: 43

Text #17

Max Range: 3.5031. Min Range: -3.5031

Max Act: 3.3313. Min Act: -0.1700

Data Index: 6588410 (Open Web Text)

Max Activating Token Index: 935

Text #18

Max Range: 3.5031. Min Range: -3.5031

Max Act: 3.2707. Min Act: -0.1700

Data Index: 754006 (Open Web Text)

Max Activating Token Index: 147

Text #19

Max Range: 3.5031. Min Range: -3.5031

Max Act: 3.2663. Min Act: -0.1700

Data Index: 1995440 (Open Web Text)

Max Activating Token Index: 383