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

Dataset: Open Web Text

Neuron 2313 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: 4.0746. Min Range: -4.0746

Max Act: 4.0746. Min Act: -0.1700

Data Index: 396090 (Open Web Text)

Max Activating Token Index: 503

Text #1

Max Range: 4.0746. Min Range: -4.0746

Max Act: 4.0009. Min Act: -0.1700

Data Index: 3966859 (Open Web Text)

Max Activating Token Index: 120

Text #2

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.9156. Min Act: -0.1700

Data Index: 1771104 (Open Web Text)

Max Activating Token Index: 913

Text #3

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.9457. Min Act: -0.1700

Data Index: 4101632 (Open Web Text)

Max Activating Token Index: 282

Text #4

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.8779. Min Act: -0.1700

Data Index: 3781293 (Open Web Text)

Max Activating Token Index: 396

Text #5

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.8345. Min Act: -0.1700

Data Index: 3561029 (Open Web Text)

Max Activating Token Index: 673

Text #6

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.8553. Min Act: -0.1700

Data Index: 3721736 (Open Web Text)

Max Activating Token Index: 341

Text #7

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.8495. Min Act: -0.1700

Data Index: 1771105 (Open Web Text)

Max Activating Token Index: 305

Text #8

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.7749. Min Act: -0.1700

Data Index: 3904618 (Open Web Text)

Max Activating Token Index: 451

Text #9

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.7621. Min Act: -0.1700

Data Index: 5692776 (Open Web Text)

Max Activating Token Index: 1022

Text #10

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.7546. Min Act: -0.1700

Data Index: 3981396 (Open Web Text)

Max Activating Token Index: 549

Text #11

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.7535. Min Act: -0.1700

Data Index: 6459639 (Open Web Text)

Max Activating Token Index: 523

Text #12

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.7510. Min Act: -0.1700

Data Index: 1698671 (Open Web Text)

Max Activating Token Index: 750

Text #13

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.7733. Min Act: -0.1700

Data Index: 7819643 (Open Web Text)

Max Activating Token Index: 638

Text #14

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.7270. Min Act: -0.1700

Data Index: 5613965 (Open Web Text)

Max Activating Token Index: 506

Text #15

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.7684. Min Act: -0.1700

Data Index: 3114498 (Open Web Text)

Max Activating Token Index: 536

Text #16

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.7042. Min Act: -0.1700

Data Index: 745215 (Open Web Text)

Max Activating Token Index: 780

Text #17

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.7416. Min Act: -0.1700

Data Index: 5472266 (Open Web Text)

Max Activating Token Index: 768

Text #18

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.7285. Min Act: -0.1700

Data Index: 6206861 (Open Web Text)

Max Activating Token Index: 672

Text #19

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.7241. Min Act: -0.1700

Data Index: 5240550 (Open Web Text)

Max Activating Token Index: 192