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

Dataset: Open Web Text

Neuron 2402 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: 3.5378. Min Range: -3.5378

Max Act: 3.5378. Min Act: -0.1700

Data Index: 5475877 (Open Web Text)

Max Activating Token Index: 710

Text #1

Max Range: 3.5378. Min Range: -3.5378

Max Act: 3.4586. Min Act: -0.1700

Data Index: 7042266 (Open Web Text)

Max Activating Token Index: 69

Text #2

Max Range: 3.5378. Min Range: -3.5378

Max Act: 3.4442. Min Act: -0.1700

Data Index: 417976 (Open Web Text)

Max Activating Token Index: 518

Text #3

Max Range: 3.5378. Min Range: -3.5378

Max Act: 3.4347. Min Act: -0.1700

Data Index: 8677641 (Open Web Text)

Max Activating Token Index: 495

Text #4

Max Range: 3.5378. Min Range: -3.5378

Max Act: 3.4423. Min Act: -0.1700

Data Index: 5738399 (Open Web Text)

Max Activating Token Index: 596

Text #5

Max Range: 3.5378. Min Range: -3.5378

Max Act: 3.4157. Min Act: -0.1700

Data Index: 8036726 (Open Web Text)

Max Activating Token Index: 282

Text #6

Max Range: 3.5378. Min Range: -3.5378

Max Act: 3.4152. Min Act: -0.1700

Data Index: 7381012 (Open Web Text)

Max Activating Token Index: 624

Text #7

Max Range: 3.5378. Min Range: -3.5378

Max Act: 3.3879. Min Act: -0.1700

Data Index: 2675328 (Open Web Text)

Max Activating Token Index: 522

Text #8

Max Range: 3.5378. Min Range: -3.5378

Max Act: 3.3884. Min Act: -0.1700

Data Index: 3189792 (Open Web Text)

Max Activating Token Index: 63

Text #9

Max Range: 3.5378. Min Range: -3.5378

Max Act: 3.3988. Min Act: -0.1700

Data Index: 6057972 (Open Web Text)

Max Activating Token Index: 606

Text #10

Max Range: 3.5378. Min Range: -3.5378

Max Act: 3.3915. Min Act: -0.1700

Data Index: 5623259 (Open Web Text)

Max Activating Token Index: 87

Text #11

Max Range: 3.5378. Min Range: -3.5378

Max Act: 3.3865. Min Act: -0.1700

Data Index: 7582141 (Open Web Text)

Max Activating Token Index: 644

Text #12

Max Range: 3.5378. Min Range: -3.5378

Max Act: 3.3718. Min Act: -0.1700

Data Index: 1682116 (Open Web Text)

Max Activating Token Index: 741

Text #13

Max Range: 3.5378. Min Range: -3.5378

Max Act: 3.3903. Min Act: -0.1700

Data Index: 4222140 (Open Web Text)

Max Activating Token Index: 622

Text #14

Max Range: 3.5378. Min Range: -3.5378

Max Act: 3.3847. Min Act: -0.1700

Data Index: 7999553 (Open Web Text)

Max Activating Token Index: 737

Text #15

Max Range: 3.5378. Min Range: -3.5378

Max Act: 3.3876. Min Act: -0.1700

Data Index: 8166362 (Open Web Text)

Max Activating Token Index: 875

Text #16

Max Range: 3.5378. Min Range: -3.5378

Max Act: 3.3657. Min Act: -0.1700

Data Index: 3922761 (Open Web Text)

Max Activating Token Index: 742

Text #17

Max Range: 3.5378. Min Range: -3.5378

Max Act: 3.3471. Min Act: -0.1700

Data Index: 502796 (Open Web Text)

Max Activating Token Index: 803

Text #18

Max Range: 3.5378. Min Range: -3.5378

Max Act: 3.3739. Min Act: -0.1700

Data Index: 3886609 (Open Web Text)

Max Activating Token Index: 442

Text #19

Max Range: 3.5378. Min Range: -3.5378

Max Act: 3.3685. Min Act: -0.1700

Data Index: 7048591 (Open Web Text)

Max Activating Token Index: 877