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

Dataset: Open Web Text

Neuron 1128 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: 5.5017. Min Range: -5.5017

Max Act: 5.5017. Min Act: -0.1700

Data Index: 1934262 (Open Web Text)

Max Activating Token Index: 375

Text #1

Max Range: 5.5017. Min Range: -5.5017

Max Act: 5.4401. Min Act: -0.1700

Data Index: 4946913 (Open Web Text)

Max Activating Token Index: 479

Text #2

Max Range: 5.5017. Min Range: -5.5017

Max Act: 5.3503. Min Act: -0.1700

Data Index: 5707438 (Open Web Text)

Max Activating Token Index: 626

Text #3

Max Range: 5.5017. Min Range: -5.5017

Max Act: 5.3613. Min Act: -0.1700

Data Index: 7048847 (Open Web Text)

Max Activating Token Index: 170

Text #4

Max Range: 5.5017. Min Range: -5.5017

Max Act: 5.3445. Min Act: -0.1700

Data Index: 7185243 (Open Web Text)

Max Activating Token Index: 169

Text #5

Max Range: 5.5017. Min Range: -5.5017

Max Act: 5.3461. Min Act: -0.1700

Data Index: 7508746 (Open Web Text)

Max Activating Token Index: 708

Text #6

Max Range: 5.5017. Min Range: -5.5017

Max Act: 5.3349. Min Act: -0.1700

Data Index: 1094875 (Open Web Text)

Max Activating Token Index: 880

Text #7

Max Range: 5.5017. Min Range: -5.5017

Max Act: 5.3038. Min Act: -0.1700

Data Index: 4591288 (Open Web Text)

Max Activating Token Index: 564

Text #8

Max Range: 5.5017. Min Range: -5.5017

Max Act: 5.3230. Min Act: -0.1700

Data Index: 7753864 (Open Web Text)

Max Activating Token Index: 143

Text #9

Max Range: 5.5017. Min Range: -5.5017

Max Act: 5.3197. Min Act: -0.1700

Data Index: 4921822 (Open Web Text)

Max Activating Token Index: 750

Text #10

Max Range: 5.5017. Min Range: -5.5017

Max Act: 5.2859. Min Act: -0.1700

Data Index: 5191556 (Open Web Text)

Max Activating Token Index: 494

Text #11

Max Range: 5.5017. Min Range: -5.5017

Max Act: 5.2892. Min Act: -0.1700

Data Index: 1084945 (Open Web Text)

Max Activating Token Index: 392

Text #12

Max Range: 5.5017. Min Range: -5.5017

Max Act: 5.3117. Min Act: -0.1700

Data Index: 7680949 (Open Web Text)

Max Activating Token Index: 648

Text #13

Max Range: 5.5017. Min Range: -5.5017

Max Act: 5.2595. Min Act: -0.1700

Data Index: 7743340 (Open Web Text)

Max Activating Token Index: 472

Text #14

Max Range: 5.5017. Min Range: -5.5017

Max Act: 5.2751. Min Act: -0.1700

Data Index: 5906249 (Open Web Text)

Max Activating Token Index: 359

Text #15

Max Range: 5.5017. Min Range: -5.5017

Max Act: 5.2443. Min Act: -0.1700

Data Index: 2663476 (Open Web Text)

Max Activating Token Index: 310

Text #16

Max Range: 5.5017. Min Range: -5.5017

Max Act: 5.2576. Min Act: -0.1700

Data Index: 3266175 (Open Web Text)

Max Activating Token Index: 714

Text #17

Max Range: 5.5017. Min Range: -5.5017

Max Act: 5.2480. Min Act: -0.1700

Data Index: 7627760 (Open Web Text)

Max Activating Token Index: 944

Text #18

Max Range: 5.5017. Min Range: -5.5017

Max Act: 5.2322. Min Act: -0.1700

Data Index: 2240845 (Open Web Text)

Max Activating Token Index: 814

Text #19

Max Range: 5.5017. Min Range: -5.5017

Max Act: 5.2305. Min Act: -0.1700

Data Index: 7215237 (Open Web Text)

Max Activating Token Index: 219