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

Dataset: Open Web Text

Neuron 2658 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: 1.3878. Min Range: -1.3878

Max Act: 1.3878. Min Act: -0.1700

Data Index: 4258689 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.3515. Min Act: -0.1698

Data Index: 2383023 (Open Web Text)

Max Activating Token Index: 746

Text #2

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.3194. Min Act: -0.1663

Data Index: 1840828 (Open Web Text)

Max Activating Token Index: 405

Text #3

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.3284. Min Act: -0.1691

Data Index: 3233119 (Open Web Text)

Max Activating Token Index: 523

Text #4

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.3383. Min Act: -0.1700

Data Index: 5955146 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.3329. Min Act: -0.1695

Data Index: 7935164 (Open Web Text)

Max Activating Token Index: 610

Text #6

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.3285. Min Act: -0.1700

Data Index: 8117272 (Open Web Text)

Max Activating Token Index: 320

Text #7

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.3257. Min Act: -0.1699

Data Index: 5860156 (Open Web Text)

Max Activating Token Index: 347

Text #8

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.3244. Min Act: -0.1700

Data Index: 5926715 (Open Web Text)

Max Activating Token Index: 51

Text #9

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.3118. Min Act: -0.1700

Data Index: 6613196 (Open Web Text)

Max Activating Token Index: 470

Text #10

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.3079. Min Act: -0.1700

Data Index: 5426271 (Open Web Text)

Max Activating Token Index: 333

Text #11

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.3071. Min Act: -0.1700

Data Index: 3979211 (Open Web Text)

Max Activating Token Index: 286

Text #12

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.3064. Min Act: -0.1695

Data Index: 5551040 (Open Web Text)

Max Activating Token Index: 170

Text #13

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.3002. Min Act: -0.1699

Data Index: 4599496 (Open Web Text)

Max Activating Token Index: 752

Text #14

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.3042. Min Act: -0.1689

Data Index: 4888687 (Open Web Text)

Max Activating Token Index: 163

Text #15

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.3014. Min Act: -0.1699

Data Index: 7790362 (Open Web Text)

Max Activating Token Index: 504

Text #16

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.2878. Min Act: -0.1700

Data Index: 3939263 (Open Web Text)

Max Activating Token Index: 531

Text #17

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.2805. Min Act: -0.1700

Data Index: 2543009 (Open Web Text)

Max Activating Token Index: 338

Text #18

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.2902. Min Act: -0.1700

Data Index: 777240 (Open Web Text)

Max Activating Token Index: 240

Text #19

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.2930. Min Act: -0.1694

Data Index: 7059383 (Open Web Text)

Max Activating Token Index: 390