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

Dataset: Open Web Text

Neuron 1863 in Layer 6

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: 2.9946. Min Range: -2.9946

Max Act: 2.9946. Min Act: -0.1700

Data Index: 4407150 (Open Web Text)

Max Activating Token Index: 40

Text #1

Max Range: 2.9946. Min Range: -2.9946

Max Act: 2.9446. Min Act: -0.1700

Data Index: 1466140 (Open Web Text)

Max Activating Token Index: 619

Text #2

Max Range: 2.9946. Min Range: -2.9946

Max Act: 2.8489. Min Act: -0.1700

Data Index: 3554694 (Open Web Text)

Max Activating Token Index: 152

Text #3

Max Range: 2.9946. Min Range: -2.9946

Max Act: 2.8396. Min Act: -0.1700

Data Index: 6298207 (Open Web Text)

Max Activating Token Index: 849

Text #4

Max Range: 2.9946. Min Range: -2.9946

Max Act: 2.8232. Min Act: -0.1700

Data Index: 891114 (Open Web Text)

Max Activating Token Index: 972

Text #5

Max Range: 2.9946. Min Range: -2.9946

Max Act: 2.7988. Min Act: -0.1700

Data Index: 2179596 (Open Web Text)

Max Activating Token Index: 887

Text #6

Max Range: 2.9946. Min Range: -2.9946

Max Act: 2.8194. Min Act: -0.1700

Data Index: 4484787 (Open Web Text)

Max Activating Token Index: 526

Text #7

Max Range: 2.9946. Min Range: -2.9946

Max Act: 2.8313. Min Act: -0.1700

Data Index: 6894654 (Open Web Text)

Max Activating Token Index: 781

Text #8

Max Range: 2.9946. Min Range: -2.9946

Max Act: 2.8210. Min Act: -0.1700

Data Index: 1793025 (Open Web Text)

Max Activating Token Index: 592

Text #9

Max Range: 2.9946. Min Range: -2.9946

Max Act: 2.7833. Min Act: -0.1700

Data Index: 3298940 (Open Web Text)

Max Activating Token Index: 601

Text #10

Max Range: 2.9946. Min Range: -2.9946

Max Act: 2.7971. Min Act: -0.1700

Data Index: 5494817 (Open Web Text)

Max Activating Token Index: 691

Text #11

Max Range: 2.9946. Min Range: -2.9946

Max Act: 2.8052. Min Act: -0.1700

Data Index: 6677829 (Open Web Text)

Max Activating Token Index: 123

Text #12

Max Range: 2.9946. Min Range: -2.9946

Max Act: 2.7932. Min Act: -0.1700

Data Index: 456702 (Open Web Text)

Max Activating Token Index: 651

Text #13

Max Range: 2.9946. Min Range: -2.9946

Max Act: 2.7981. Min Act: -0.1700

Data Index: 5631926 (Open Web Text)

Max Activating Token Index: 33

Text #14

Max Range: 2.9946. Min Range: -2.9946

Max Act: 2.7943. Min Act: -0.1700

Data Index: 41248 (Open Web Text)

Max Activating Token Index: 791

Text #15

Max Range: 2.9946. Min Range: -2.9946

Max Act: 2.7956. Min Act: -0.1700

Data Index: 7927323 (Open Web Text)

Max Activating Token Index: 478

Text #16

Max Range: 2.9946. Min Range: -2.9946

Max Act: 2.7990. Min Act: -0.1700

Data Index: 4695418 (Open Web Text)

Max Activating Token Index: 344

Text #17

Max Range: 2.9946. Min Range: -2.9946

Max Act: 2.7783. Min Act: -0.1700

Data Index: 4347235 (Open Web Text)

Max Activating Token Index: 565

Text #18

Max Range: 2.9946. Min Range: -2.9946

Max Act: 2.7606. Min Act: -0.1700

Data Index: 3884537 (Open Web Text)

Max Activating Token Index: 391

Text #19

Max Range: 2.9946. Min Range: -2.9946

Max Act: 2.7705. Min Act: -0.1700

Data Index: 367425 (Open Web Text)

Max Activating Token Index: 96