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

Dataset: Open Web Text

Neuron 2654 in Layer 5

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: 3.3722. Min Range: -3.3722

Max Act: 3.3556. Min Act: -0.1700

Data Index: 8704290 (Open Web Text)

Max Activating Token Index: 55

Text #1

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.3722. Min Act: -0.1700

Data Index: 2835010 (Open Web Text)

Max Activating Token Index: 956

Text #2

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.3566. Min Act: -0.1700

Data Index: 5969597 (Open Web Text)

Max Activating Token Index: 996

Text #3

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.3251. Min Act: -0.1700

Data Index: 5364635 (Open Web Text)

Max Activating Token Index: 423

Text #4

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.3109. Min Act: -0.1700

Data Index: 5219903 (Open Web Text)

Max Activating Token Index: 187

Text #5

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.3249. Min Act: -0.1700

Data Index: 5990599 (Open Web Text)

Max Activating Token Index: 625

Text #6

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2830. Min Act: -0.1700

Data Index: 4020626 (Open Web Text)

Max Activating Token Index: 448

Text #7

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2735. Min Act: -0.1700

Data Index: 503297 (Open Web Text)

Max Activating Token Index: 984

Text #8

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2623. Min Act: -0.1700

Data Index: 5862077 (Open Web Text)

Max Activating Token Index: 959

Text #9

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2466. Min Act: -0.1700

Data Index: 4533329 (Open Web Text)

Max Activating Token Index: 680

Text #10

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2564. Min Act: -0.1700

Data Index: 5872761 (Open Web Text)

Max Activating Token Index: 685

Text #11

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2392. Min Act: -0.1700

Data Index: 3520999 (Open Web Text)

Max Activating Token Index: 635

Text #12

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2260. Min Act: -0.1700

Data Index: 4454903 (Open Web Text)

Max Activating Token Index: 480

Text #13

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2446. Min Act: -0.1700

Data Index: 66946 (Open Web Text)

Max Activating Token Index: 152

Text #14

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2496. Min Act: -0.1700

Data Index: 461458 (Open Web Text)

Max Activating Token Index: 54

Text #15

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2550. Min Act: -0.1700

Data Index: 8669248 (Open Web Text)

Max Activating Token Index: 762

Text #16

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2265. Min Act: -0.1700

Data Index: 5872760 (Open Web Text)

Max Activating Token Index: 794

Text #17

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2302. Min Act: -0.1700

Data Index: 3484087 (Open Web Text)

Max Activating Token Index: 176

Text #18

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2066. Min Act: -0.1700

Data Index: 466162 (Open Web Text)

Max Activating Token Index: 914

Text #19

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2203. Min Act: -0.1700

Data Index: 1869653 (Open Web Text)

Max Activating Token Index: 915