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

Dataset: Open Web Text

Neuron 1734 in Layer 1

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: 2.3593. Min Range: -2.3593

Max Act: 2.3593. Min Act: -0.1700

Data Index: 453014 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 2.3593. Min Range: -2.3593

Max Act: 2.2814. Min Act: -0.1700

Data Index: 7599110 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 2.3593. Min Range: -2.3593

Max Act: 2.2576. Min Act: -0.1700

Data Index: 8248141 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 2.3593. Min Range: -2.3593

Max Act: 2.2390. Min Act: -0.1700

Data Index: 4299970 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 2.3593. Min Range: -2.3593

Max Act: 2.2333. Min Act: -0.1700

Data Index: 5737496 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 2.3593. Min Range: -2.3593

Max Act: 2.2115. Min Act: -0.1700

Data Index: 2383674 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 2.3593. Min Range: -2.3593

Max Act: 2.2164. Min Act: -0.1700

Data Index: 5391078 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 2.3593. Min Range: -2.3593

Max Act: 2.1993. Min Act: -0.1700

Data Index: 2271664 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 2.3593. Min Range: -2.3593

Max Act: 2.2108. Min Act: -0.1700

Data Index: 3596845 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 2.3593. Min Range: -2.3593

Max Act: 2.1664. Min Act: -0.1700

Data Index: 1320850 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 2.3593. Min Range: -2.3593

Max Act: 2.1556. Min Act: -0.1700

Data Index: 5669581 (Open Web Text)

Max Activating Token Index: 19

Text #11

Max Range: 2.3593. Min Range: -2.3593

Max Act: 2.1550. Min Act: -0.1700

Data Index: 7554327 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 2.3593. Min Range: -2.3593

Max Act: 2.1496. Min Act: -0.1700

Data Index: 8780448 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 2.3593. Min Range: -2.3593

Max Act: 2.1489. Min Act: -0.1700

Data Index: 947194 (Open Web Text)

Max Activating Token Index: 457

Text #14

Max Range: 2.3593. Min Range: -2.3593

Max Act: 2.1380. Min Act: -0.1700

Data Index: 2531887 (Open Web Text)

Max Activating Token Index: 425

Text #15

Max Range: 2.3593. Min Range: -2.3593

Max Act: 2.1499. Min Act: -0.1700

Data Index: 5299352 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 2.3593. Min Range: -2.3593

Max Act: 2.1561. Min Act: -0.1700

Data Index: 3022287 (Open Web Text)

Max Activating Token Index: 544

Text #17

Max Range: 2.3593. Min Range: -2.3593

Max Act: 2.1334. Min Act: -0.1700

Data Index: 3802188 (Open Web Text)

Max Activating Token Index: 14

Text #18

Max Range: 2.3593. Min Range: -2.3593

Max Act: 2.1482. Min Act: -0.1700

Data Index: 2735666 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 2.3593. Min Range: -2.3593

Max Act: 2.1406. Min Act: -0.1700

Data Index: 4752240 (Open Web Text)

Max Activating Token Index: 28