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

Dataset: Open Web Text

Neuron 408 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: 6.4864. Min Range: -6.4864

Max Act: 6.4864. Min Act: -0.1700

Data Index: 4671974 (Open Web Text)

Max Activating Token Index: 11

Text #1

Max Range: 6.4864. Min Range: -6.4864

Max Act: 6.4499. Min Act: -0.1700

Data Index: 7975042 (Open Web Text)

Max Activating Token Index: 113

Text #2

Max Range: 6.4864. Min Range: -6.4864

Max Act: 6.3663. Min Act: -0.1700

Data Index: 7399794 (Open Web Text)

Max Activating Token Index: 757

Text #3

Max Range: 6.4864. Min Range: -6.4864

Max Act: 6.3134. Min Act: -0.1700

Data Index: 3673564 (Open Web Text)

Max Activating Token Index: 79

Text #4

Max Range: 6.4864. Min Range: -6.4864

Max Act: 6.3059. Min Act: -0.1700

Data Index: 1532996 (Open Web Text)

Max Activating Token Index: 19

Text #5

Max Range: 6.4864. Min Range: -6.4864

Max Act: 6.3296. Min Act: -0.1700

Data Index: 5538692 (Open Web Text)

Max Activating Token Index: 167

Text #6

Max Range: 6.4864. Min Range: -6.4864

Max Act: 6.2895. Min Act: -0.1700

Data Index: 5921732 (Open Web Text)

Max Activating Token Index: 184

Text #7

Max Range: 6.4864. Min Range: -6.4864

Max Act: 6.2578. Min Act: -0.1700

Data Index: 3693825 (Open Web Text)

Max Activating Token Index: 528

Text #8

Max Range: 6.4864. Min Range: -6.4864

Max Act: 6.2024. Min Act: -0.1700

Data Index: 2680500 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 6.4864. Min Range: -6.4864

Max Act: 6.1897. Min Act: -0.1700

Data Index: 782924 (Open Web Text)

Max Activating Token Index: 332

Text #10

Max Range: 6.4864. Min Range: -6.4864

Max Act: 6.1773. Min Act: -0.1700

Data Index: 977259 (Open Web Text)

Max Activating Token Index: 517

Text #11

Max Range: 6.4864. Min Range: -6.4864

Max Act: 6.2321. Min Act: -0.1700

Data Index: 5713711 (Open Web Text)

Max Activating Token Index: 831

Text #12

Max Range: 6.4864. Min Range: -6.4864

Max Act: 6.1909. Min Act: -0.1700

Data Index: 2950667 (Open Web Text)

Max Activating Token Index: 25

Text #13

Max Range: 6.4864. Min Range: -6.4864

Max Act: 6.1405. Min Act: -0.1700

Data Index: 642644 (Open Web Text)

Max Activating Token Index: 220

Text #14

Max Range: 6.4864. Min Range: -6.4864

Max Act: 6.1566. Min Act: -0.1700

Data Index: 1266429 (Open Web Text)

Max Activating Token Index: 290

Text #15

Max Range: 6.4864. Min Range: -6.4864

Max Act: 6.1773. Min Act: -0.1700

Data Index: 252096 (Open Web Text)

Max Activating Token Index: 16

Text #16

Max Range: 6.4864. Min Range: -6.4864

Max Act: 6.1375. Min Act: -0.1700

Data Index: 3528670 (Open Web Text)

Max Activating Token Index: 897

Text #17

Max Range: 6.4864. Min Range: -6.4864

Max Act: 6.1033. Min Act: -0.1700

Data Index: 3003841 (Open Web Text)

Max Activating Token Index: 242

Text #18

Max Range: 6.4864. Min Range: -6.4864

Max Act: 6.1260. Min Act: -0.1700

Data Index: 2640298 (Open Web Text)

Max Activating Token Index: 16

Text #19

Max Range: 6.4864. Min Range: -6.4864

Max Act: 6.0975. Min Act: -0.1700

Data Index: 6731606 (Open Web Text)

Max Activating Token Index: 179