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

Dataset: Open Web Text

Neuron 668 in Layer 3

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: 3.3734. Min Range: -3.3734

Max Act: 3.3723. Min Act: -0.1700

Data Index: 6873066 (Open Web Text)

Max Activating Token Index: 602

Text #1

Max Range: 3.3734. Min Range: -3.3734

Max Act: 3.3734. Min Act: -0.1700

Data Index: 3734304 (Open Web Text)

Max Activating Token Index: 553

Text #2

Max Range: 3.3734. Min Range: -3.3734

Max Act: 3.3506. Min Act: -0.1700

Data Index: 8522912 (Open Web Text)

Max Activating Token Index: 592

Text #3

Max Range: 3.3734. Min Range: -3.3734

Max Act: 3.3381. Min Act: -0.1700

Data Index: 1826115 (Open Web Text)

Max Activating Token Index: 416

Text #4

Max Range: 3.3734. Min Range: -3.3734

Max Act: 3.2962. Min Act: -0.1700

Data Index: 6127331 (Open Web Text)

Max Activating Token Index: 524

Text #5

Max Range: 3.3734. Min Range: -3.3734

Max Act: 3.3481. Min Act: -0.1700

Data Index: 7338578 (Open Web Text)

Max Activating Token Index: 458

Text #6

Max Range: 3.3734. Min Range: -3.3734

Max Act: 3.3152. Min Act: -0.1700

Data Index: 6712433 (Open Web Text)

Max Activating Token Index: 472

Text #7

Max Range: 3.3734. Min Range: -3.3734

Max Act: 3.2851. Min Act: -0.1700

Data Index: 7537726 (Open Web Text)

Max Activating Token Index: 724

Text #8

Max Range: 3.3734. Min Range: -3.3734

Max Act: 3.3200. Min Act: -0.1700

Data Index: 716592 (Open Web Text)

Max Activating Token Index: 627

Text #9

Max Range: 3.3734. Min Range: -3.3734

Max Act: 3.3070. Min Act: -0.1700

Data Index: 3410060 (Open Web Text)

Max Activating Token Index: 436

Text #10

Max Range: 3.3734. Min Range: -3.3734

Max Act: 3.2846. Min Act: -0.1700

Data Index: 886600 (Open Web Text)

Max Activating Token Index: 213

Text #11

Max Range: 3.3734. Min Range: -3.3734

Max Act: 3.3090. Min Act: -0.1700

Data Index: 6386857 (Open Web Text)

Max Activating Token Index: 333

Text #12

Max Range: 3.3734. Min Range: -3.3734

Max Act: 3.2678. Min Act: -0.1700

Data Index: 5709523 (Open Web Text)

Max Activating Token Index: 699

Text #13

Max Range: 3.3734. Min Range: -3.3734

Max Act: 3.2392. Min Act: -0.1700

Data Index: 1310029 (Open Web Text)

Max Activating Token Index: 887

Text #14

Max Range: 3.3734. Min Range: -3.3734

Max Act: 3.2525. Min Act: -0.1700

Data Index: 3069135 (Open Web Text)

Max Activating Token Index: 968

Text #15

Max Range: 3.3734. Min Range: -3.3734

Max Act: 3.2617. Min Act: -0.1700

Data Index: 3102126 (Open Web Text)

Max Activating Token Index: 303

Text #16

Max Range: 3.3734. Min Range: -3.3734

Max Act: 3.2515. Min Act: -0.1700

Data Index: 3222250 (Open Web Text)

Max Activating Token Index: 472

Text #17

Max Range: 3.3734. Min Range: -3.3734

Max Act: 3.2602. Min Act: -0.1700

Data Index: 2783008 (Open Web Text)

Max Activating Token Index: 895

Text #18

Max Range: 3.3734. Min Range: -3.3734

Max Act: 3.2607. Min Act: -0.1700

Data Index: 2483967 (Open Web Text)

Max Activating Token Index: 734

Text #19

Max Range: 3.3734. Min Range: -3.3734

Max Act: 3.2690. Min Act: -0.1700

Data Index: 5590501 (Open Web Text)

Max Activating Token Index: 300