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

Dataset: Open Web Text

Neuron 1564 in Layer 1

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: 1.9552. Min Range: -1.9552

Max Act: 1.9552. Min Act: -0.1700

Data Index: 2284326 (Open Web Text)

Max Activating Token Index: 144

Text #1

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.9500. Min Act: -0.1700

Data Index: 4268022 (Open Web Text)

Max Activating Token Index: 817

Text #2

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.9509. Min Act: -0.1700

Data Index: 6561490 (Open Web Text)

Max Activating Token Index: 965

Text #3

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.9534. Min Act: -0.1700

Data Index: 6262937 (Open Web Text)

Max Activating Token Index: 87

Text #4

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.9342. Min Act: -0.1700

Data Index: 4343040 (Open Web Text)

Max Activating Token Index: 987

Text #5

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.9375. Min Act: -0.1700

Data Index: 1191056 (Open Web Text)

Max Activating Token Index: 138

Text #6

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.9296. Min Act: -0.1700

Data Index: 6658917 (Open Web Text)

Max Activating Token Index: 376

Text #7

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.9334. Min Act: -0.1700

Data Index: 2192851 (Open Web Text)

Max Activating Token Index: 78

Text #8

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.9257. Min Act: -0.1700

Data Index: 6523580 (Open Web Text)

Max Activating Token Index: 655

Text #9

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.9357. Min Act: -0.1700

Data Index: 6174619 (Open Web Text)

Max Activating Token Index: 897

Text #10

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.9372. Min Act: -0.1700

Data Index: 7840024 (Open Web Text)

Max Activating Token Index: 412

Text #11

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.9070. Min Act: -0.1698

Data Index: 2773521 (Open Web Text)

Max Activating Token Index: 617

Text #12

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.9163. Min Act: -0.1700

Data Index: 5185733 (Open Web Text)

Max Activating Token Index: 306

Text #13

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.9290. Min Act: -0.1700

Data Index: 7133751 (Open Web Text)

Max Activating Token Index: 986

Text #14

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.9036. Min Act: -0.1700

Data Index: 3782404 (Open Web Text)

Max Activating Token Index: 986

Text #15

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.9002. Min Act: -0.1700

Data Index: 6067101 (Open Web Text)

Max Activating Token Index: 554

Text #16

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.8947. Min Act: -0.1700

Data Index: 1818222 (Open Web Text)

Max Activating Token Index: 529

Text #17

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.8971. Min Act: -0.1699

Data Index: 1017686 (Open Web Text)

Max Activating Token Index: 821

Text #18

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.8956. Min Act: -0.1699

Data Index: 5000732 (Open Web Text)

Max Activating Token Index: 113

Text #19

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.8936. Min Act: -0.1700

Data Index: 6839621 (Open Web Text)

Max Activating Token Index: 116