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

Dataset: Open Web Text

Neuron 1728 in Layer 4

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: 4.4124. Min Range: -4.4124

Max Act: 4.4124. Min Act: -0.1700

Data Index: 6293134 (Open Web Text)

Max Activating Token Index: 831

Text #1

Max Range: 4.4124. Min Range: -4.4124

Max Act: 4.3674. Min Act: -0.1700

Data Index: 4690307 (Open Web Text)

Max Activating Token Index: 436

Text #2

Max Range: 4.4124. Min Range: -4.4124

Max Act: 4.3120. Min Act: -0.1700

Data Index: 2356604 (Open Web Text)

Max Activating Token Index: 550

Text #3

Max Range: 4.4124. Min Range: -4.4124

Max Act: 4.3263. Min Act: -0.1700

Data Index: 5929575 (Open Web Text)

Max Activating Token Index: 770

Text #4

Max Range: 4.4124. Min Range: -4.4124

Max Act: 4.2880. Min Act: -0.1700

Data Index: 3827729 (Open Web Text)

Max Activating Token Index: 975

Text #5

Max Range: 4.4124. Min Range: -4.4124

Max Act: 4.2617. Min Act: -0.1700

Data Index: 4711269 (Open Web Text)

Max Activating Token Index: 484

Text #6

Max Range: 4.4124. Min Range: -4.4124

Max Act: 4.2526. Min Act: -0.1700

Data Index: 6691892 (Open Web Text)

Max Activating Token Index: 413

Text #7

Max Range: 4.4124. Min Range: -4.4124

Max Act: 4.2671. Min Act: -0.1700

Data Index: 8034701 (Open Web Text)

Max Activating Token Index: 164

Text #8

Max Range: 4.4124. Min Range: -4.4124

Max Act: 4.2456. Min Act: -0.1700

Data Index: 3462694 (Open Web Text)

Max Activating Token Index: 968

Text #9

Max Range: 4.4124. Min Range: -4.4124

Max Act: 4.1997. Min Act: -0.1700

Data Index: 3727796 (Open Web Text)

Max Activating Token Index: 309

Text #10

Max Range: 4.4124. Min Range: -4.4124

Max Act: 4.2014. Min Act: -0.1700

Data Index: 7560832 (Open Web Text)

Max Activating Token Index: 931

Text #11

Max Range: 4.4124. Min Range: -4.4124

Max Act: 4.2595. Min Act: -0.1700

Data Index: 2694834 (Open Web Text)

Max Activating Token Index: 755

Text #12

Max Range: 4.4124. Min Range: -4.4124

Max Act: 4.2004. Min Act: -0.1700

Data Index: 4134402 (Open Web Text)

Max Activating Token Index: 958

Text #13

Max Range: 4.4124. Min Range: -4.4124

Max Act: 4.1970. Min Act: -0.1700

Data Index: 3877806 (Open Web Text)

Max Activating Token Index: 228

Text #14

Max Range: 4.4124. Min Range: -4.4124

Max Act: 4.1819. Min Act: -0.1700

Data Index: 63948 (Open Web Text)

Max Activating Token Index: 726

Text #15

Max Range: 4.4124. Min Range: -4.4124

Max Act: 4.1854. Min Act: -0.1700

Data Index: 447189 (Open Web Text)

Max Activating Token Index: 692

Text #16

Max Range: 4.4124. Min Range: -4.4124

Max Act: 4.1973. Min Act: -0.1700

Data Index: 3981309 (Open Web Text)

Max Activating Token Index: 689

Text #17

Max Range: 4.4124. Min Range: -4.4124

Max Act: 4.1368. Min Act: -0.1700

Data Index: 3813835 (Open Web Text)

Max Activating Token Index: 361

Text #18

Max Range: 4.4124. Min Range: -4.4124

Max Act: 4.1499. Min Act: -0.1700

Data Index: 2673574 (Open Web Text)

Max Activating Token Index: 680

Text #19

Max Range: 4.4124. Min Range: -4.4124

Max Act: 4.1883. Min Act: -0.1700

Data Index: 6781600 (Open Web Text)

Max Activating Token Index: 826