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

Dataset: Open Web Text

Neuron 1826 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: 4.4291. Min Range: -4.4291

Max Act: 4.4291. Min Act: -0.1700

Data Index: 4312967 (Open Web Text)

Max Activating Token Index: 518

Text #1

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.3847. Min Act: -0.1700

Data Index: 7094076 (Open Web Text)

Max Activating Token Index: 885

Text #2

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.3536. Min Act: -0.1700

Data Index: 5542174 (Open Web Text)

Max Activating Token Index: 402

Text #3

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.3370. Min Act: -0.1700

Data Index: 8076688 (Open Web Text)

Max Activating Token Index: 320

Text #4

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.3169. Min Act: -0.1700

Data Index: 8806022 (Open Web Text)

Max Activating Token Index: 464

Text #5

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.2964. Min Act: -0.1700

Data Index: 112187 (Open Web Text)

Max Activating Token Index: 180

Text #6

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.3108. Min Act: -0.1700

Data Index: 8440597 (Open Web Text)

Max Activating Token Index: 550

Text #7

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.3109. Min Act: -0.1700

Data Index: 6204576 (Open Web Text)

Max Activating Token Index: 504

Text #8

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.2905. Min Act: -0.1700

Data Index: 180664 (Open Web Text)

Max Activating Token Index: 497

Text #9

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.3014. Min Act: -0.1700

Data Index: 5508214 (Open Web Text)

Max Activating Token Index: 188

Text #10

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.2549. Min Act: -0.1700

Data Index: 2476163 (Open Web Text)

Max Activating Token Index: 770

Text #11

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.2719. Min Act: -0.1700

Data Index: 3335284 (Open Web Text)

Max Activating Token Index: 613

Text #12

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.2520. Min Act: -0.1700

Data Index: 6383855 (Open Web Text)

Max Activating Token Index: 941

Text #13

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.2560. Min Act: -0.1700

Data Index: 6385616 (Open Web Text)

Max Activating Token Index: 393

Text #14

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.2147. Min Act: -0.1700

Data Index: 2327192 (Open Web Text)

Max Activating Token Index: 957

Text #15

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.2705. Min Act: -0.1700

Data Index: 5097465 (Open Web Text)

Max Activating Token Index: 777

Text #16

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.2547. Min Act: -0.1700

Data Index: 2565794 (Open Web Text)

Max Activating Token Index: 548

Text #17

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.2396. Min Act: -0.1700

Data Index: 8399160 (Open Web Text)

Max Activating Token Index: 575

Text #18

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.2213. Min Act: -0.1700

Data Index: 811708 (Open Web Text)

Max Activating Token Index: 779

Text #19

Max Range: 4.4291. Min Range: -4.4291

Max Act: 4.2521. Min Act: -0.1700

Data Index: 5512460 (Open Web Text)

Max Activating Token Index: 564