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

Dataset: Open Web Text

Neuron 1490 in Layer 1

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: 4.3906. Min Range: -4.3906

Max Act: 4.3906. Min Act: -0.1700

Data Index: 5800809 (Open Web Text)

Max Activating Token Index: 556

Text #1

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.3478. Min Act: -0.1700

Data Index: 4161988 (Open Web Text)

Max Activating Token Index: 598

Text #2

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.3197. Min Act: -0.1700

Data Index: 2670208 (Open Web Text)

Max Activating Token Index: 103

Text #3

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.3237. Min Act: -0.1700

Data Index: 3935915 (Open Web Text)

Max Activating Token Index: 681

Text #4

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.3003. Min Act: -0.1700

Data Index: 2003337 (Open Web Text)

Max Activating Token Index: 569

Text #5

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.3163. Min Act: -0.1700

Data Index: 1895825 (Open Web Text)

Max Activating Token Index: 237

Text #6

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.3024. Min Act: -0.1700

Data Index: 1009770 (Open Web Text)

Max Activating Token Index: 762

Text #7

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.3008. Min Act: -0.1700

Data Index: 7854286 (Open Web Text)

Max Activating Token Index: 541

Text #8

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.3041. Min Act: -0.1700

Data Index: 3994664 (Open Web Text)

Max Activating Token Index: 61

Text #9

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.2820. Min Act: -0.1700

Data Index: 1494550 (Open Web Text)

Max Activating Token Index: 573

Text #10

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.2893. Min Act: -0.1700

Data Index: 1804512 (Open Web Text)

Max Activating Token Index: 312

Text #11

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.2861. Min Act: -0.1700

Data Index: 4380732 (Open Web Text)

Max Activating Token Index: 475

Text #12

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.2751. Min Act: -0.1700

Data Index: 4624283 (Open Web Text)

Max Activating Token Index: 664

Text #13

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.2895. Min Act: -0.1700

Data Index: 2929450 (Open Web Text)

Max Activating Token Index: 485

Text #14

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.2671. Min Act: -0.1700

Data Index: 3269987 (Open Web Text)

Max Activating Token Index: 575

Text #15

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.2795. Min Act: -0.1700

Data Index: 3286859 (Open Web Text)

Max Activating Token Index: 261

Text #16

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.2757. Min Act: -0.1700

Data Index: 5500250 (Open Web Text)

Max Activating Token Index: 696

Text #17

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.2634. Min Act: -0.1700

Data Index: 3322745 (Open Web Text)

Max Activating Token Index: 255

Text #18

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.2656. Min Act: -0.1700

Data Index: 3460191 (Open Web Text)

Max Activating Token Index: 747

Text #19

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.2608. Min Act: -0.1700

Data Index: 3920495 (Open Web Text)

Max Activating Token Index: 603