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

Dataset: Open Web Text

Neuron 1959 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: 3.1038. Min Range: -3.1038

Max Act: 3.1038. Min Act: -0.1700

Data Index: 2149356 (Open Web Text)

Max Activating Token Index: 205

Text #1

Max Range: 3.1038. Min Range: -3.1038

Max Act: 3.0586. Min Act: -0.1700

Data Index: 828247 (Open Web Text)

Max Activating Token Index: 802

Text #2

Max Range: 3.1038. Min Range: -3.1038

Max Act: 3.0808. Min Act: -0.1700

Data Index: 3670097 (Open Web Text)

Max Activating Token Index: 260

Text #3

Max Range: 3.1038. Min Range: -3.1038

Max Act: 3.0924. Min Act: -0.1700

Data Index: 6783599 (Open Web Text)

Max Activating Token Index: 947

Text #4

Max Range: 3.1038. Min Range: -3.1038

Max Act: 3.0736. Min Act: -0.1700

Data Index: 6132954 (Open Web Text)

Max Activating Token Index: 51

Text #5

Max Range: 3.1038. Min Range: -3.1038

Max Act: 3.0597. Min Act: -0.1700

Data Index: 2795399 (Open Web Text)

Max Activating Token Index: 915

Text #6

Max Range: 3.1038. Min Range: -3.1038

Max Act: 3.0559. Min Act: -0.1700

Data Index: 6844536 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 3.1038. Min Range: -3.1038

Max Act: 3.0479. Min Act: -0.1700

Data Index: 6754068 (Open Web Text)

Max Activating Token Index: 654

Text #8

Max Range: 3.1038. Min Range: -3.1038

Max Act: 3.0687. Min Act: -0.1700

Data Index: 5042935 (Open Web Text)

Max Activating Token Index: 108

Text #9

Max Range: 3.1038. Min Range: -3.1038

Max Act: 3.0432. Min Act: -0.1700

Data Index: 6350637 (Open Web Text)

Max Activating Token Index: 530

Text #10

Max Range: 3.1038. Min Range: -3.1038

Max Act: 3.0256. Min Act: -0.1700

Data Index: 2876760 (Open Web Text)

Max Activating Token Index: 989

Text #11

Max Range: 3.1038. Min Range: -3.1038

Max Act: 3.0440. Min Act: -0.1700

Data Index: 8765117 (Open Web Text)

Max Activating Token Index: 652

Text #12

Max Range: 3.1038. Min Range: -3.1038

Max Act: 3.0232. Min Act: -0.1700

Data Index: 2040236 (Open Web Text)

Max Activating Token Index: 379

Text #13

Max Range: 3.1038. Min Range: -3.1038

Max Act: 3.0427. Min Act: -0.1700

Data Index: 2671865 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 3.1038. Min Range: -3.1038

Max Act: 3.0327. Min Act: -0.1700

Data Index: 7479068 (Open Web Text)

Max Activating Token Index: 1009

Text #15

Max Range: 3.1038. Min Range: -3.1038

Max Act: 3.0371. Min Act: -0.1700

Data Index: 4209712 (Open Web Text)

Max Activating Token Index: 14

Text #16

Max Range: 3.1038. Min Range: -3.1038

Max Act: 3.0351. Min Act: -0.1700

Data Index: 3947040 (Open Web Text)

Max Activating Token Index: 368

Text #17

Max Range: 3.1038. Min Range: -3.1038

Max Act: 3.0280. Min Act: -0.1700

Data Index: 5281541 (Open Web Text)

Max Activating Token Index: 34

Text #18

Max Range: 3.1038. Min Range: -3.1038

Max Act: 3.0173. Min Act: -0.1700

Data Index: 6123971 (Open Web Text)

Max Activating Token Index: 563

Text #19

Max Range: 3.1038. Min Range: -3.1038

Max Act: 3.0487. Min Act: -0.1700

Data Index: 8661239 (Open Web Text)

Max Activating Token Index: 836