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

Dataset: Open Web Text

Neuron 2233 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: 4.8801. Min Range: -4.8801

Max Act: 4.8485. Min Act: -0.1700

Data Index: 6038371 (Open Web Text)

Max Activating Token Index: 99

Text #1

Max Range: 4.8801. Min Range: -4.8801

Max Act: 4.8801. Min Act: -0.1700

Data Index: 5457481 (Open Web Text)

Max Activating Token Index: 464

Text #2

Max Range: 4.8801. Min Range: -4.8801

Max Act: 4.8633. Min Act: -0.1700

Data Index: 6038369 (Open Web Text)

Max Activating Token Index: 823

Text #3

Max Range: 4.8801. Min Range: -4.8801

Max Act: 4.8305. Min Act: -0.1700

Data Index: 4223775 (Open Web Text)

Max Activating Token Index: 272

Text #4

Max Range: 4.8801. Min Range: -4.8801

Max Act: 4.7929. Min Act: -0.1700

Data Index: 321082 (Open Web Text)

Max Activating Token Index: 726

Text #5

Max Range: 4.8801. Min Range: -4.8801

Max Act: 4.7566. Min Act: -0.1700

Data Index: 1407493 (Open Web Text)

Max Activating Token Index: 771

Text #6

Max Range: 4.8801. Min Range: -4.8801

Max Act: 4.7505. Min Act: -0.1700

Data Index: 3246508 (Open Web Text)

Max Activating Token Index: 565

Text #7

Max Range: 4.8801. Min Range: -4.8801

Max Act: 4.7428. Min Act: -0.1700

Data Index: 491649 (Open Web Text)

Max Activating Token Index: 99

Text #8

Max Range: 4.8801. Min Range: -4.8801

Max Act: 4.7752. Min Act: -0.1700

Data Index: 2251801 (Open Web Text)

Max Activating Token Index: 1015

Text #9

Max Range: 4.8801. Min Range: -4.8801

Max Act: 4.7470. Min Act: -0.1700

Data Index: 1008370 (Open Web Text)

Max Activating Token Index: 263

Text #10

Max Range: 4.8801. Min Range: -4.8801

Max Act: 4.7391. Min Act: -0.1700

Data Index: 6198418 (Open Web Text)

Max Activating Token Index: 432

Text #11

Max Range: 4.8801. Min Range: -4.8801

Max Act: 4.7131. Min Act: -0.1700

Data Index: 2496869 (Open Web Text)

Max Activating Token Index: 298

Text #12

Max Range: 4.8801. Min Range: -4.8801

Max Act: 4.7318. Min Act: -0.1700

Data Index: 7070028 (Open Web Text)

Max Activating Token Index: 790

Text #13

Max Range: 4.8801. Min Range: -4.8801

Max Act: 4.7402. Min Act: -0.1700

Data Index: 6958818 (Open Web Text)

Max Activating Token Index: 505

Text #14

Max Range: 4.8801. Min Range: -4.8801

Max Act: 4.6956. Min Act: -0.1700

Data Index: 5294251 (Open Web Text)

Max Activating Token Index: 184

Text #15

Max Range: 4.8801. Min Range: -4.8801

Max Act: 4.6911. Min Act: -0.1700

Data Index: 3292646 (Open Web Text)

Max Activating Token Index: 144

Text #16

Max Range: 4.8801. Min Range: -4.8801

Max Act: 4.7193. Min Act: -0.1700

Data Index: 4600934 (Open Web Text)

Max Activating Token Index: 152

Text #17

Max Range: 4.8801. Min Range: -4.8801

Max Act: 4.6793. Min Act: -0.1700

Data Index: 2102991 (Open Web Text)

Max Activating Token Index: 571

Text #18

Max Range: 4.8801. Min Range: -4.8801

Max Act: 4.7113. Min Act: -0.1700

Data Index: 7465957 (Open Web Text)

Max Activating Token Index: 230

Text #19

Max Range: 4.8801. Min Range: -4.8801

Max Act: 4.6584. Min Act: -0.1700

Data Index: 2833512 (Open Web Text)

Max Activating Token Index: 468