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

Dataset: Open Web Text

Neuron 2464 in Layer 3

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: 4.1231. Min Range: -4.1231

Max Act: 4.1231. Min Act: -0.1700

Data Index: 3935049 (Open Web Text)

Max Activating Token Index: 319

Text #1

Max Range: 4.1231. Min Range: -4.1231

Max Act: 4.0584. Min Act: -0.1700

Data Index: 8078502 (Open Web Text)

Max Activating Token Index: 709

Text #2

Max Range: 4.1231. Min Range: -4.1231

Max Act: 3.9852. Min Act: -0.1700

Data Index: 3515415 (Open Web Text)

Max Activating Token Index: 83

Text #3

Max Range: 4.1231. Min Range: -4.1231

Max Act: 4.0194. Min Act: -0.1700

Data Index: 6292391 (Open Web Text)

Max Activating Token Index: 552

Text #4

Max Range: 4.1231. Min Range: -4.1231

Max Act: 3.9589. Min Act: -0.1700

Data Index: 8829573 (Open Web Text)

Max Activating Token Index: 733

Text #5

Max Range: 4.1231. Min Range: -4.1231

Max Act: 3.9531. Min Act: -0.1700

Data Index: 1013680 (Open Web Text)

Max Activating Token Index: 633

Text #6

Max Range: 4.1231. Min Range: -4.1231

Max Act: 3.9240. Min Act: -0.1700

Data Index: 6700342 (Open Web Text)

Max Activating Token Index: 108

Text #7

Max Range: 4.1231. Min Range: -4.1231

Max Act: 3.9450. Min Act: -0.1700

Data Index: 3935047 (Open Web Text)

Max Activating Token Index: 408

Text #8

Max Range: 4.1231. Min Range: -4.1231

Max Act: 3.9337. Min Act: -0.1700

Data Index: 5939737 (Open Web Text)

Max Activating Token Index: 1003

Text #9

Max Range: 4.1231. Min Range: -4.1231

Max Act: 3.9078. Min Act: -0.1700

Data Index: 1296062 (Open Web Text)

Max Activating Token Index: 714

Text #10

Max Range: 4.1231. Min Range: -4.1231

Max Act: 3.8845. Min Act: -0.1700

Data Index: 4461196 (Open Web Text)

Max Activating Token Index: 88

Text #11

Max Range: 4.1231. Min Range: -4.1231

Max Act: 3.8972. Min Act: -0.1700

Data Index: 3173363 (Open Web Text)

Max Activating Token Index: 50

Text #12

Max Range: 4.1231. Min Range: -4.1231

Max Act: 3.8673. Min Act: -0.1700

Data Index: 718655 (Open Web Text)

Max Activating Token Index: 180

Text #13

Max Range: 4.1231. Min Range: -4.1231

Max Act: 3.8665. Min Act: -0.1700

Data Index: 6799086 (Open Web Text)

Max Activating Token Index: 479

Text #14

Max Range: 4.1231. Min Range: -4.1231

Max Act: 3.8712. Min Act: -0.1700

Data Index: 3527399 (Open Web Text)

Max Activating Token Index: 541

Text #15

Max Range: 4.1231. Min Range: -4.1231

Max Act: 3.8675. Min Act: -0.1700

Data Index: 3786270 (Open Web Text)

Max Activating Token Index: 540

Text #16

Max Range: 4.1231. Min Range: -4.1231

Max Act: 3.8729. Min Act: -0.1700

Data Index: 3946394 (Open Web Text)

Max Activating Token Index: 1021

Text #17

Max Range: 4.1231. Min Range: -4.1231

Max Act: 3.8644. Min Act: -0.1700

Data Index: 1991136 (Open Web Text)

Max Activating Token Index: 417

Text #18

Max Range: 4.1231. Min Range: -4.1231

Max Act: 3.8728. Min Act: -0.1700

Data Index: 6464173 (Open Web Text)

Max Activating Token Index: 124

Text #19

Max Range: 4.1231. Min Range: -4.1231

Max Act: 3.8192. Min Act: -0.1700

Data Index: 841661 (Open Web Text)

Max Activating Token Index: 540