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

Dataset: Open Web Text

Neuron 1636 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: 3.2231. Min Range: -3.2231

Max Act: 3.2231. Min Act: -0.1700

Data Index: 1070729 (Open Web Text)

Max Activating Token Index: 487

Text #1

Max Range: 3.2231. Min Range: -3.2231

Max Act: 3.0449. Min Act: -0.1700

Data Index: 4778615 (Open Web Text)

Max Activating Token Index: 320

Text #2

Max Range: 3.2231. Min Range: -3.2231

Max Act: 3.0881. Min Act: -0.1700

Data Index: 2784598 (Open Web Text)

Max Activating Token Index: 345

Text #3

Max Range: 3.2231. Min Range: -3.2231

Max Act: 3.0671. Min Act: -0.1700

Data Index: 4236441 (Open Web Text)

Max Activating Token Index: 482

Text #4

Max Range: 3.2231. Min Range: -3.2231

Max Act: 2.9755. Min Act: -0.1700

Data Index: 655207 (Open Web Text)

Max Activating Token Index: 690

Text #5

Max Range: 3.2231. Min Range: -3.2231

Max Act: 3.0148. Min Act: -0.1700

Data Index: 2117192 (Open Web Text)

Max Activating Token Index: 357

Text #6

Max Range: 3.2231. Min Range: -3.2231

Max Act: 3.0359. Min Act: -0.1700

Data Index: 6489800 (Open Web Text)

Max Activating Token Index: 522

Text #7

Max Range: 3.2231. Min Range: -3.2231

Max Act: 2.9849. Min Act: -0.1700

Data Index: 7887991 (Open Web Text)

Max Activating Token Index: 224

Text #8

Max Range: 3.2231. Min Range: -3.2231

Max Act: 3.0144. Min Act: -0.1700

Data Index: 4939078 (Open Web Text)

Max Activating Token Index: 771

Text #9

Max Range: 3.2231. Min Range: -3.2231

Max Act: 2.9423. Min Act: -0.1700

Data Index: 6322822 (Open Web Text)

Max Activating Token Index: 441

Text #10

Max Range: 3.2231. Min Range: -3.2231

Max Act: 2.9482. Min Act: -0.1700

Data Index: 8355145 (Open Web Text)

Max Activating Token Index: 612

Text #11

Max Range: 3.2231. Min Range: -3.2231

Max Act: 2.9538. Min Act: -0.1700

Data Index: 1761820 (Open Web Text)

Max Activating Token Index: 271

Text #12

Max Range: 3.2231. Min Range: -3.2231

Max Act: 2.9469. Min Act: -0.1700

Data Index: 2613840 (Open Web Text)

Max Activating Token Index: 872

Text #13

Max Range: 3.2231. Min Range: -3.2231

Max Act: 2.9331. Min Act: -0.1700

Data Index: 7996042 (Open Web Text)

Max Activating Token Index: 349

Text #14

Max Range: 3.2231. Min Range: -3.2231

Max Act: 2.9528. Min Act: -0.1700

Data Index: 6293933 (Open Web Text)

Max Activating Token Index: 491

Text #15

Max Range: 3.2231. Min Range: -3.2231

Max Act: 2.9040. Min Act: -0.1700

Data Index: 2323760 (Open Web Text)

Max Activating Token Index: 639

Text #16

Max Range: 3.2231. Min Range: -3.2231

Max Act: 2.9272. Min Act: -0.1700

Data Index: 4907054 (Open Web Text)

Max Activating Token Index: 716

Text #17

Max Range: 3.2231. Min Range: -3.2231

Max Act: 2.9070. Min Act: -0.1700

Data Index: 1215133 (Open Web Text)

Max Activating Token Index: 28

Text #18

Max Range: 3.2231. Min Range: -3.2231

Max Act: 2.8593. Min Act: -0.1700

Data Index: 3764576 (Open Web Text)

Max Activating Token Index: 548

Text #19

Max Range: 3.2231. Min Range: -3.2231

Max Act: 2.9001. Min Act: -0.1700

Data Index: 2775008 (Open Web Text)

Max Activating Token Index: 716