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

Dataset: Open Web Text

Neuron 456 in Layer 0

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: 5.5275. Min Range: -5.5275

Max Act: 5.5275. Min Act: -0.1700

Data Index: 1785141 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 5.5275. Min Range: -5.5275

Max Act: 5.3549. Min Act: -0.1700

Data Index: 4312244 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 5.5275. Min Range: -5.5275

Max Act: 5.3099. Min Act: -0.1700

Data Index: 7315134 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 5.5275. Min Range: -5.5275

Max Act: 5.3105. Min Act: -0.1700

Data Index: 4575028 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 5.5275. Min Range: -5.5275

Max Act: 5.2842. Min Act: -0.1700

Data Index: 2669313 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 5.5275. Min Range: -5.5275

Max Act: 5.2694. Min Act: -0.1700

Data Index: 5931827 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 5.5275. Min Range: -5.5275

Max Act: 5.2672. Min Act: -0.1700

Data Index: 3892829 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 5.5275. Min Range: -5.5275

Max Act: 5.2430. Min Act: -0.1700

Data Index: 7668798 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 5.5275. Min Range: -5.5275

Max Act: 5.2601. Min Act: -0.1700

Data Index: 7783516 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 5.5275. Min Range: -5.5275

Max Act: 5.2272. Min Act: -0.1700

Data Index: 7966821 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 5.5275. Min Range: -5.5275

Max Act: 5.2017. Min Act: -0.1700

Data Index: 108231 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 5.5275. Min Range: -5.5275

Max Act: 5.1662. Min Act: -0.1700

Data Index: 1192495 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 5.5275. Min Range: -5.5275

Max Act: 5.1781. Min Act: -0.1700

Data Index: 518613 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 5.5275. Min Range: -5.5275

Max Act: 5.1674. Min Act: -0.1700

Data Index: 5513375 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 5.5275. Min Range: -5.5275

Max Act: 5.1555. Min Act: -0.1700

Data Index: 5615353 (Open Web Text)

Max Activating Token Index: 916

Text #15

Max Range: 5.5275. Min Range: -5.5275

Max Act: 5.1331. Min Act: -0.1700

Data Index: 2213928 (Open Web Text)

Max Activating Token Index: 14

Text #16

Max Range: 5.5275. Min Range: -5.5275

Max Act: 5.1456. Min Act: -0.1700

Data Index: 5276048 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 5.5275. Min Range: -5.5275

Max Act: 5.1572. Min Act: -0.1700

Data Index: 5159498 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 5.5275. Min Range: -5.5275

Max Act: 5.1484. Min Act: -0.1700

Data Index: 193394 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 5.5275. Min Range: -5.5275

Max Act: 5.1517. Min Act: -0.1700

Data Index: 4750528 (Open Web Text)

Max Activating Token Index: 6