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

Dataset: Open Web Text

Neuron 554 in Layer 6

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: 4.9480. Min Range: -4.9480

Max Act: 4.9480. Min Act: -0.1700

Data Index: 5973739 (Open Web Text)

Max Activating Token Index: 546

Text #1

Max Range: 4.9480. Min Range: -4.9480

Max Act: 4.9251. Min Act: -0.1700

Data Index: 845807 (Open Web Text)

Max Activating Token Index: 396

Text #2

Max Range: 4.9480. Min Range: -4.9480

Max Act: 4.8721. Min Act: -0.1700

Data Index: 5298396 (Open Web Text)

Max Activating Token Index: 578

Text #3

Max Range: 4.9480. Min Range: -4.9480

Max Act: 4.8821. Min Act: -0.1700

Data Index: 451823 (Open Web Text)

Max Activating Token Index: 408

Text #4

Max Range: 4.9480. Min Range: -4.9480

Max Act: 4.8868. Min Act: -0.1700

Data Index: 5903325 (Open Web Text)

Max Activating Token Index: 687

Text #5

Max Range: 4.9480. Min Range: -4.9480

Max Act: 4.8773. Min Act: -0.1700

Data Index: 8373481 (Open Web Text)

Max Activating Token Index: 216

Text #6

Max Range: 4.9480. Min Range: -4.9480

Max Act: 4.8311. Min Act: -0.1700

Data Index: 5607328 (Open Web Text)

Max Activating Token Index: 205

Text #7

Max Range: 4.9480. Min Range: -4.9480

Max Act: 4.8351. Min Act: -0.1700

Data Index: 2299071 (Open Web Text)

Max Activating Token Index: 74

Text #8

Max Range: 4.9480. Min Range: -4.9480

Max Act: 4.8081. Min Act: -0.1700

Data Index: 4642823 (Open Web Text)

Max Activating Token Index: 792

Text #9

Max Range: 4.9480. Min Range: -4.9480

Max Act: 4.8258. Min Act: -0.1700

Data Index: 6301701 (Open Web Text)

Max Activating Token Index: 387

Text #10

Max Range: 4.9480. Min Range: -4.9480

Max Act: 4.8458. Min Act: -0.1700

Data Index: 4970733 (Open Web Text)

Max Activating Token Index: 873

Text #11

Max Range: 4.9480. Min Range: -4.9480

Max Act: 4.8020. Min Act: -0.1700

Data Index: 659674 (Open Web Text)

Max Activating Token Index: 94

Text #12

Max Range: 4.9480. Min Range: -4.9480

Max Act: 4.7962. Min Act: -0.1700

Data Index: 2663391 (Open Web Text)

Max Activating Token Index: 275

Text #13

Max Range: 4.9480. Min Range: -4.9480

Max Act: 4.7990. Min Act: -0.1700

Data Index: 5415620 (Open Web Text)

Max Activating Token Index: 749

Text #14

Max Range: 4.9480. Min Range: -4.9480

Max Act: 4.8178. Min Act: -0.1700

Data Index: 5760332 (Open Web Text)

Max Activating Token Index: 726

Text #15

Max Range: 4.9480. Min Range: -4.9480

Max Act: 4.8136. Min Act: -0.1700

Data Index: 1964811 (Open Web Text)

Max Activating Token Index: 913

Text #16

Max Range: 4.9480. Min Range: -4.9480

Max Act: 4.8203. Min Act: -0.1700

Data Index: 1401270 (Open Web Text)

Max Activating Token Index: 302

Text #17

Max Range: 4.9480. Min Range: -4.9480

Max Act: 4.7528. Min Act: -0.1700

Data Index: 2216741 (Open Web Text)

Max Activating Token Index: 628

Text #18

Max Range: 4.9480. Min Range: -4.9480

Max Act: 4.7706. Min Act: -0.1700

Data Index: 4521853 (Open Web Text)

Max Activating Token Index: 638

Text #19

Max Range: 4.9480. Min Range: -4.9480

Max Act: 4.7865. Min Act: -0.1700

Data Index: 1089122 (Open Web Text)

Max Activating Token Index: 10