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

Dataset: Open Web Text

Neuron 1960 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: 3.0296. Min Range: -3.0296

Max Act: 3.0296. Min Act: -0.1700

Data Index: 2161384 (Open Web Text)

Max Activating Token Index: 875

Text #1

Max Range: 3.0296. Min Range: -3.0296

Max Act: 3.0027. Min Act: -0.1700

Data Index: 4098920 (Open Web Text)

Max Activating Token Index: 997

Text #2

Max Range: 3.0296. Min Range: -3.0296

Max Act: 2.9442. Min Act: -0.1700

Data Index: 1529433 (Open Web Text)

Max Activating Token Index: 208

Text #3

Max Range: 3.0296. Min Range: -3.0296

Max Act: 2.9309. Min Act: -0.1700

Data Index: 7762606 (Open Web Text)

Max Activating Token Index: 642

Text #4

Max Range: 3.0296. Min Range: -3.0296

Max Act: 2.9170. Min Act: -0.1700

Data Index: 3457027 (Open Web Text)

Max Activating Token Index: 386

Text #5

Max Range: 3.0296. Min Range: -3.0296

Max Act: 2.9099. Min Act: -0.1700

Data Index: 5513349 (Open Web Text)

Max Activating Token Index: 823

Text #6

Max Range: 3.0296. Min Range: -3.0296

Max Act: 2.8996. Min Act: -0.1700

Data Index: 894538 (Open Web Text)

Max Activating Token Index: 454

Text #7

Max Range: 3.0296. Min Range: -3.0296

Max Act: 2.8899. Min Act: -0.1700

Data Index: 7113640 (Open Web Text)

Max Activating Token Index: 225

Text #8

Max Range: 3.0296. Min Range: -3.0296

Max Act: 2.9002. Min Act: -0.1700

Data Index: 2577038 (Open Web Text)

Max Activating Token Index: 757

Text #9

Max Range: 3.0296. Min Range: -3.0296

Max Act: 2.8682. Min Act: -0.1700

Data Index: 8790237 (Open Web Text)

Max Activating Token Index: 911

Text #10

Max Range: 3.0296. Min Range: -3.0296

Max Act: 2.8670. Min Act: -0.1700

Data Index: 7400079 (Open Web Text)

Max Activating Token Index: 912

Text #11

Max Range: 3.0296. Min Range: -3.0296

Max Act: 2.8630. Min Act: -0.1700

Data Index: 1594626 (Open Web Text)

Max Activating Token Index: 817

Text #12

Max Range: 3.0296. Min Range: -3.0296

Max Act: 2.8564. Min Act: -0.1700

Data Index: 8657237 (Open Web Text)

Max Activating Token Index: 543

Text #13

Max Range: 3.0296. Min Range: -3.0296

Max Act: 2.8630. Min Act: -0.1700

Data Index: 2590509 (Open Web Text)

Max Activating Token Index: 521

Text #14

Max Range: 3.0296. Min Range: -3.0296

Max Act: 2.8532. Min Act: -0.1700

Data Index: 310173 (Open Web Text)

Max Activating Token Index: 466

Text #15

Max Range: 3.0296. Min Range: -3.0296

Max Act: 2.8711. Min Act: -0.1700

Data Index: 4544251 (Open Web Text)

Max Activating Token Index: 923

Text #16

Max Range: 3.0296. Min Range: -3.0296

Max Act: 2.8674. Min Act: -0.1700

Data Index: 5236788 (Open Web Text)

Max Activating Token Index: 981

Text #17

Max Range: 3.0296. Min Range: -3.0296

Max Act: 2.8261. Min Act: -0.1700

Data Index: 7209185 (Open Web Text)

Max Activating Token Index: 88

Text #18

Max Range: 3.0296. Min Range: -3.0296

Max Act: 2.8722. Min Act: -0.1700

Data Index: 6137758 (Open Web Text)

Max Activating Token Index: 440

Text #19

Max Range: 3.0296. Min Range: -3.0296

Max Act: 2.8273. Min Act: -0.1700

Data Index: 35886 (Open Web Text)

Max Activating Token Index: 466