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

Dataset: Open Web Text

Neuron 2438 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: 4.4864. Min Range: -4.4864

Max Act: 4.4864. Min Act: -0.1700

Data Index: 6658296 (Open Web Text)

Max Activating Token Index: 500

Text #1

Max Range: 4.4864. Min Range: -4.4864

Max Act: 4.4289. Min Act: -0.1700

Data Index: 6457850 (Open Web Text)

Max Activating Token Index: 314

Text #2

Max Range: 4.4864. Min Range: -4.4864

Max Act: 4.3833. Min Act: -0.1700

Data Index: 1679952 (Open Web Text)

Max Activating Token Index: 774

Text #3

Max Range: 4.4864. Min Range: -4.4864

Max Act: 4.3892. Min Act: -0.1700

Data Index: 3373615 (Open Web Text)

Max Activating Token Index: 573

Text #4

Max Range: 4.4864. Min Range: -4.4864

Max Act: 4.3650. Min Act: -0.1700

Data Index: 2923949 (Open Web Text)

Max Activating Token Index: 815

Text #5

Max Range: 4.4864. Min Range: -4.4864

Max Act: 4.3699. Min Act: -0.1700

Data Index: 7325027 (Open Web Text)

Max Activating Token Index: 517

Text #6

Max Range: 4.4864. Min Range: -4.4864

Max Act: 4.3511. Min Act: -0.1700

Data Index: 6294171 (Open Web Text)

Max Activating Token Index: 459

Text #7

Max Range: 4.4864. Min Range: -4.4864

Max Act: 4.3535. Min Act: -0.1700

Data Index: 7226863 (Open Web Text)

Max Activating Token Index: 281

Text #8

Max Range: 4.4864. Min Range: -4.4864

Max Act: 4.3188. Min Act: -0.1700

Data Index: 6455611 (Open Web Text)

Max Activating Token Index: 443

Text #9

Max Range: 4.4864. Min Range: -4.4864

Max Act: 4.3311. Min Act: -0.1700

Data Index: 4261876 (Open Web Text)

Max Activating Token Index: 688

Text #10

Max Range: 4.4864. Min Range: -4.4864

Max Act: 4.2867. Min Act: -0.1700

Data Index: 885092 (Open Web Text)

Max Activating Token Index: 742

Text #11

Max Range: 4.4864. Min Range: -4.4864

Max Act: 4.3134. Min Act: -0.1700

Data Index: 1972044 (Open Web Text)

Max Activating Token Index: 585

Text #12

Max Range: 4.4864. Min Range: -4.4864

Max Act: 4.2878. Min Act: -0.1700

Data Index: 4504532 (Open Web Text)

Max Activating Token Index: 833

Text #13

Max Range: 4.4864. Min Range: -4.4864

Max Act: 4.3248. Min Act: -0.1700

Data Index: 4764412 (Open Web Text)

Max Activating Token Index: 690

Text #14

Max Range: 4.4864. Min Range: -4.4864

Max Act: 4.3034. Min Act: -0.1700

Data Index: 7942077 (Open Web Text)

Max Activating Token Index: 33

Text #15

Max Range: 4.4864. Min Range: -4.4864

Max Act: 4.2977. Min Act: -0.1700

Data Index: 3864659 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 4.4864. Min Range: -4.4864

Max Act: 4.2928. Min Act: -0.1700

Data Index: 5319274 (Open Web Text)

Max Activating Token Index: 70

Text #17

Max Range: 4.4864. Min Range: -4.4864

Max Act: 4.2893. Min Act: -0.1700

Data Index: 6853942 (Open Web Text)

Max Activating Token Index: 19

Text #18

Max Range: 4.4864. Min Range: -4.4864

Max Act: 4.2522. Min Act: -0.1700

Data Index: 220573 (Open Web Text)

Max Activating Token Index: 313

Text #19

Max Range: 4.4864. Min Range: -4.4864

Max Act: 4.2490. Min Act: -0.1700

Data Index: 5138575 (Open Web Text)

Max Activating Token Index: 472