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

Dataset: Open Web Text

Neuron 1304 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: 4.0395. Min Range: -4.0395

Max Act: 4.0395. Min Act: -0.1700

Data Index: 7253604 (Open Web Text)

Max Activating Token Index: 866

Text #1

Max Range: 4.0395. Min Range: -4.0395

Max Act: 3.9103. Min Act: -0.1700

Data Index: 8135460 (Open Web Text)

Max Activating Token Index: 962

Text #2

Max Range: 4.0395. Min Range: -4.0395

Max Act: 3.9237. Min Act: -0.1700

Data Index: 6565083 (Open Web Text)

Max Activating Token Index: 98

Text #3

Max Range: 4.0395. Min Range: -4.0395

Max Act: 3.8463. Min Act: -0.1700

Data Index: 565814 (Open Web Text)

Max Activating Token Index: 407

Text #4

Max Range: 4.0395. Min Range: -4.0395

Max Act: 3.8248. Min Act: -0.1700

Data Index: 4192062 (Open Web Text)

Max Activating Token Index: 44

Text #5

Max Range: 4.0395. Min Range: -4.0395

Max Act: 3.8375. Min Act: -0.1700

Data Index: 4834762 (Open Web Text)

Max Activating Token Index: 619

Text #6

Max Range: 4.0395. Min Range: -4.0395

Max Act: 3.7556. Min Act: -0.1700

Data Index: 2130865 (Open Web Text)

Max Activating Token Index: 376

Text #7

Max Range: 4.0395. Min Range: -4.0395

Max Act: 3.7935. Min Act: -0.1700

Data Index: 1549971 (Open Web Text)

Max Activating Token Index: 764

Text #8

Max Range: 4.0395. Min Range: -4.0395

Max Act: 3.7335. Min Act: -0.1700

Data Index: 7763453 (Open Web Text)

Max Activating Token Index: 263

Text #9

Max Range: 4.0395. Min Range: -4.0395

Max Act: 3.7158. Min Act: -0.1700

Data Index: 6944141 (Open Web Text)

Max Activating Token Index: 698

Text #10

Max Range: 4.0395. Min Range: -4.0395

Max Act: 3.7086. Min Act: -0.1700

Data Index: 4052951 (Open Web Text)

Max Activating Token Index: 469

Text #11

Max Range: 4.0395. Min Range: -4.0395

Max Act: 3.7069. Min Act: -0.1700

Data Index: 1908119 (Open Web Text)

Max Activating Token Index: 70

Text #12

Max Range: 4.0395. Min Range: -4.0395

Max Act: 3.7380. Min Act: -0.1700

Data Index: 990534 (Open Web Text)

Max Activating Token Index: 808

Text #13

Max Range: 4.0395. Min Range: -4.0395

Max Act: 3.6904. Min Act: -0.1700

Data Index: 2236259 (Open Web Text)

Max Activating Token Index: 286

Text #14

Max Range: 4.0395. Min Range: -4.0395

Max Act: 3.6996. Min Act: -0.1700

Data Index: 3887132 (Open Web Text)

Max Activating Token Index: 962

Text #15

Max Range: 4.0395. Min Range: -4.0395

Max Act: 3.7209. Min Act: -0.1700

Data Index: 4496787 (Open Web Text)

Max Activating Token Index: 147

Text #16

Max Range: 4.0395. Min Range: -4.0395

Max Act: 3.7044. Min Act: -0.1700

Data Index: 7566080 (Open Web Text)

Max Activating Token Index: 389

Text #17

Max Range: 4.0395. Min Range: -4.0395

Max Act: 3.6754. Min Act: -0.1700

Data Index: 5565046 (Open Web Text)

Max Activating Token Index: 111

Text #18

Max Range: 4.0395. Min Range: -4.0395

Max Act: 3.6702. Min Act: -0.1700

Data Index: 4418123 (Open Web Text)

Max Activating Token Index: 205

Text #19

Max Range: 4.0395. Min Range: -4.0395

Max Act: 3.7016. Min Act: -0.1700

Data Index: 6019716 (Open Web Text)

Max Activating Token Index: 102