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

Dataset: Open Web Text

Neuron 366 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: 3.0474. Min Range: -3.0474

Max Act: 3.0474. Min Act: -0.1700

Data Index: 4149517 (Open Web Text)

Max Activating Token Index: 255

Text #1

Max Range: 3.0474. Min Range: -3.0474

Max Act: 2.9548. Min Act: -0.1700

Data Index: 8384214 (Open Web Text)

Max Activating Token Index: 325

Text #2

Max Range: 3.0474. Min Range: -3.0474

Max Act: 2.9477. Min Act: -0.1700

Data Index: 7070376 (Open Web Text)

Max Activating Token Index: 388

Text #3

Max Range: 3.0474. Min Range: -3.0474

Max Act: 2.8881. Min Act: -0.1700

Data Index: 7474556 (Open Web Text)

Max Activating Token Index: 935

Text #4

Max Range: 3.0474. Min Range: -3.0474

Max Act: 2.8665. Min Act: -0.1700

Data Index: 3159028 (Open Web Text)

Max Activating Token Index: 931

Text #5

Max Range: 3.0474. Min Range: -3.0474

Max Act: 2.8903. Min Act: -0.1700

Data Index: 3996565 (Open Web Text)

Max Activating Token Index: 845

Text #6

Max Range: 3.0474. Min Range: -3.0474

Max Act: 2.8553. Min Act: -0.1700

Data Index: 3163916 (Open Web Text)

Max Activating Token Index: 751

Text #7

Max Range: 3.0474. Min Range: -3.0474

Max Act: 2.8558. Min Act: -0.1700

Data Index: 7153708 (Open Web Text)

Max Activating Token Index: 522

Text #8

Max Range: 3.0474. Min Range: -3.0474

Max Act: 2.8327. Min Act: -0.1700

Data Index: 3514132 (Open Web Text)

Max Activating Token Index: 962

Text #9

Max Range: 3.0474. Min Range: -3.0474

Max Act: 2.8270. Min Act: -0.1700

Data Index: 454581 (Open Web Text)

Max Activating Token Index: 797

Text #10

Max Range: 3.0474. Min Range: -3.0474

Max Act: 2.8487. Min Act: -0.1700

Data Index: 8377296 (Open Web Text)

Max Activating Token Index: 1011

Text #11

Max Range: 3.0474. Min Range: -3.0474

Max Act: 2.8439. Min Act: -0.1700

Data Index: 3054740 (Open Web Text)

Max Activating Token Index: 1015

Text #12

Max Range: 3.0474. Min Range: -3.0474

Max Act: 2.8178. Min Act: -0.1700

Data Index: 7153707 (Open Web Text)

Max Activating Token Index: 852

Text #13

Max Range: 3.0474. Min Range: -3.0474

Max Act: 2.8183. Min Act: -0.1700

Data Index: 3961033 (Open Web Text)

Max Activating Token Index: 795

Text #14

Max Range: 3.0474. Min Range: -3.0474

Max Act: 2.8017. Min Act: -0.1700

Data Index: 3964749 (Open Web Text)

Max Activating Token Index: 114

Text #15

Max Range: 3.0474. Min Range: -3.0474

Max Act: 2.8092. Min Act: -0.1700

Data Index: 49111 (Open Web Text)

Max Activating Token Index: 421

Text #16

Max Range: 3.0474. Min Range: -3.0474

Max Act: 2.8453. Min Act: -0.1700

Data Index: 3449257 (Open Web Text)

Max Activating Token Index: 435

Text #17

Max Range: 3.0474. Min Range: -3.0474

Max Act: 2.7978. Min Act: -0.1700

Data Index: 7103610 (Open Web Text)

Max Activating Token Index: 399

Text #18

Max Range: 3.0474. Min Range: -3.0474

Max Act: 2.8296. Min Act: -0.1700

Data Index: 8255255 (Open Web Text)

Max Activating Token Index: 773

Text #19

Max Range: 3.0474. Min Range: -3.0474

Max Act: 2.7743. Min Act: -0.1700

Data Index: 4207908 (Open Web Text)

Max Activating Token Index: 362