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

Dataset: Open Web Text

Neuron 507 in Layer 4

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: 3.8801. Min Range: -3.8801

Max Act: 3.8801. Min Act: -0.1700

Data Index: 3275036 (Open Web Text)

Max Activating Token Index: 523

Text #1

Max Range: 3.8801. Min Range: -3.8801

Max Act: 3.8630. Min Act: -0.1700

Data Index: 1814338 (Open Web Text)

Max Activating Token Index: 526

Text #2

Max Range: 3.8801. Min Range: -3.8801

Max Act: 3.7981. Min Act: -0.1700

Data Index: 711609 (Open Web Text)

Max Activating Token Index: 590

Text #3

Max Range: 3.8801. Min Range: -3.8801

Max Act: 3.7855. Min Act: -0.1700

Data Index: 6169142 (Open Web Text)

Max Activating Token Index: 466

Text #4

Max Range: 3.8801. Min Range: -3.8801

Max Act: 3.7872. Min Act: -0.1700

Data Index: 3581493 (Open Web Text)

Max Activating Token Index: 1000

Text #5

Max Range: 3.8801. Min Range: -3.8801

Max Act: 3.7771. Min Act: -0.1700

Data Index: 4729094 (Open Web Text)

Max Activating Token Index: 129

Text #6

Max Range: 3.8801. Min Range: -3.8801

Max Act: 3.7982. Min Act: -0.1700

Data Index: 5128636 (Open Web Text)

Max Activating Token Index: 558

Text #7

Max Range: 3.8801. Min Range: -3.8801

Max Act: 3.7800. Min Act: -0.1700

Data Index: 2848725 (Open Web Text)

Max Activating Token Index: 388

Text #8

Max Range: 3.8801. Min Range: -3.8801

Max Act: 3.7493. Min Act: -0.1700

Data Index: 5996975 (Open Web Text)

Max Activating Token Index: 894

Text #9

Max Range: 3.8801. Min Range: -3.8801

Max Act: 3.7421. Min Act: -0.1700

Data Index: 7394206 (Open Web Text)

Max Activating Token Index: 580

Text #10

Max Range: 3.8801. Min Range: -3.8801

Max Act: 3.7193. Min Act: -0.1700

Data Index: 2259741 (Open Web Text)

Max Activating Token Index: 258

Text #11

Max Range: 3.8801. Min Range: -3.8801

Max Act: 3.7021. Min Act: -0.1700

Data Index: 5813427 (Open Web Text)

Max Activating Token Index: 121

Text #12

Max Range: 3.8801. Min Range: -3.8801

Max Act: 3.6943. Min Act: -0.1700

Data Index: 5760193 (Open Web Text)

Max Activating Token Index: 865

Text #13

Max Range: 3.8801. Min Range: -3.8801

Max Act: 3.6884. Min Act: -0.1700

Data Index: 555297 (Open Web Text)

Max Activating Token Index: 653

Text #14

Max Range: 3.8801. Min Range: -3.8801

Max Act: 3.6862. Min Act: -0.1700

Data Index: 5668299 (Open Web Text)

Max Activating Token Index: 51

Text #15

Max Range: 3.8801. Min Range: -3.8801

Max Act: 3.7333. Min Act: -0.1700

Data Index: 5251029 (Open Web Text)

Max Activating Token Index: 444

Text #16

Max Range: 3.8801. Min Range: -3.8801

Max Act: 3.6875. Min Act: -0.1700

Data Index: 4839933 (Open Web Text)

Max Activating Token Index: 462

Text #17

Max Range: 3.8801. Min Range: -3.8801

Max Act: 3.6785. Min Act: -0.1700

Data Index: 4779715 (Open Web Text)

Max Activating Token Index: 473

Text #18

Max Range: 3.8801. Min Range: -3.8801

Max Act: 3.6632. Min Act: -0.1700

Data Index: 1364477 (Open Web Text)

Max Activating Token Index: 1021

Text #19

Max Range: 3.8801. Min Range: -3.8801

Max Act: 3.7463. Min Act: -0.1700

Data Index: 3723941 (Open Web Text)

Max Activating Token Index: 926