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

Dataset: Open Web Text

Neuron 2261 in Layer 2

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: 3.4550. Min Range: -3.4550

Max Act: 3.4550. Min Act: -0.1700

Data Index: 6818911 (Open Web Text)

Max Activating Token Index: 154

Text #1

Max Range: 3.4550. Min Range: -3.4550

Max Act: 3.4405. Min Act: -0.1700

Data Index: 5388018 (Open Web Text)

Max Activating Token Index: 852

Text #2

Max Range: 3.4550. Min Range: -3.4550

Max Act: 3.4440. Min Act: -0.1700

Data Index: 1439630 (Open Web Text)

Max Activating Token Index: 152

Text #3

Max Range: 3.4550. Min Range: -3.4550

Max Act: 3.3771. Min Act: -0.1700

Data Index: 4146515 (Open Web Text)

Max Activating Token Index: 576

Text #4

Max Range: 3.4550. Min Range: -3.4550

Max Act: 3.4106. Min Act: -0.1700

Data Index: 230832 (Open Web Text)

Max Activating Token Index: 102

Text #5

Max Range: 3.4550. Min Range: -3.4550

Max Act: 3.4024. Min Act: -0.1700

Data Index: 1503291 (Open Web Text)

Max Activating Token Index: 210

Text #6

Max Range: 3.4550. Min Range: -3.4550

Max Act: 3.3619. Min Act: -0.1700

Data Index: 5589839 (Open Web Text)

Max Activating Token Index: 419

Text #7

Max Range: 3.4550. Min Range: -3.4550

Max Act: 3.3613. Min Act: -0.1700

Data Index: 6140296 (Open Web Text)

Max Activating Token Index: 295

Text #8

Max Range: 3.4550. Min Range: -3.4550

Max Act: 3.3625. Min Act: -0.1700

Data Index: 7219624 (Open Web Text)

Max Activating Token Index: 457

Text #9

Max Range: 3.4550. Min Range: -3.4550

Max Act: 3.3075. Min Act: -0.1700

Data Index: 4728728 (Open Web Text)

Max Activating Token Index: 986

Text #10

Max Range: 3.4550. Min Range: -3.4550

Max Act: 3.2952. Min Act: -0.1700

Data Index: 5020126 (Open Web Text)

Max Activating Token Index: 236

Text #11

Max Range: 3.4550. Min Range: -3.4550

Max Act: 3.3423. Min Act: -0.1700

Data Index: 7495710 (Open Web Text)

Max Activating Token Index: 34

Text #12

Max Range: 3.4550. Min Range: -3.4550

Max Act: 3.3230. Min Act: -0.1700

Data Index: 2685948 (Open Web Text)

Max Activating Token Index: 217

Text #13

Max Range: 3.4550. Min Range: -3.4550

Max Act: 3.2723. Min Act: -0.1700

Data Index: 788069 (Open Web Text)

Max Activating Token Index: 469

Text #14

Max Range: 3.4550. Min Range: -3.4550

Max Act: 3.3545. Min Act: -0.1700

Data Index: 1757024 (Open Web Text)

Max Activating Token Index: 1010

Text #15

Max Range: 3.4550. Min Range: -3.4550

Max Act: 3.2412. Min Act: -0.1700

Data Index: 274206 (Open Web Text)

Max Activating Token Index: 571

Text #16

Max Range: 3.4550. Min Range: -3.4550

Max Act: 3.3059. Min Act: -0.1700

Data Index: 4516351 (Open Web Text)

Max Activating Token Index: 676

Text #17

Max Range: 3.4550. Min Range: -3.4550

Max Act: 3.2749. Min Act: -0.1700

Data Index: 36169 (Open Web Text)

Max Activating Token Index: 712

Text #18

Max Range: 3.4550. Min Range: -3.4550

Max Act: 3.2713. Min Act: -0.1700

Data Index: 6049725 (Open Web Text)

Max Activating Token Index: 961

Text #19

Max Range: 3.4550. Min Range: -3.4550

Max Act: 3.3016. Min Act: -0.1700

Data Index: 1366207 (Open Web Text)

Max Activating Token Index: 71