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

Dataset: Open Web Text

Neuron 2210 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: 4.2755. Min Range: -4.2755

Max Act: 4.2703. Min Act: -0.1694

Data Index: 6057507 (Open Web Text)

Max Activating Token Index: 946

Text #1

Max Range: 4.2755. Min Range: -4.2755

Max Act: 4.2755. Min Act: -0.1674

Data Index: 2886312 (Open Web Text)

Max Activating Token Index: 803

Text #2

Max Range: 4.2755. Min Range: -4.2755

Max Act: 4.1334. Min Act: -0.1700

Data Index: 8307291 (Open Web Text)

Max Activating Token Index: 786

Text #3

Max Range: 4.2755. Min Range: -4.2755

Max Act: 4.1184. Min Act: -0.1697

Data Index: 276339 (Open Web Text)

Max Activating Token Index: 77

Text #4

Max Range: 4.2755. Min Range: -4.2755

Max Act: 4.0794. Min Act: -0.1699

Data Index: 5836402 (Open Web Text)

Max Activating Token Index: 944

Text #5

Max Range: 4.2755. Min Range: -4.2755

Max Act: 4.0609. Min Act: -0.1700

Data Index: 6864950 (Open Web Text)

Max Activating Token Index: 632

Text #6

Max Range: 4.2755. Min Range: -4.2755

Max Act: 4.0707. Min Act: -0.1700

Data Index: 226584 (Open Web Text)

Max Activating Token Index: 682

Text #7

Max Range: 4.2755. Min Range: -4.2755

Max Act: 4.0407. Min Act: -0.1687

Data Index: 873523 (Open Web Text)

Max Activating Token Index: 870

Text #8

Max Range: 4.2755. Min Range: -4.2755

Max Act: 4.0013. Min Act: -0.1699

Data Index: 5374608 (Open Web Text)

Max Activating Token Index: 443

Text #9

Max Range: 4.2755. Min Range: -4.2755

Max Act: 4.0544. Min Act: -0.1700

Data Index: 265922 (Open Web Text)

Max Activating Token Index: 443

Text #10

Max Range: 4.2755. Min Range: -4.2755

Max Act: 4.0055. Min Act: -0.1698

Data Index: 2856332 (Open Web Text)

Max Activating Token Index: 842

Text #11

Max Range: 4.2755. Min Range: -4.2755

Max Act: 4.0055. Min Act: -0.1700

Data Index: 3332226 (Open Web Text)

Max Activating Token Index: 159

Text #12

Max Range: 4.2755. Min Range: -4.2755

Max Act: 3.9270. Min Act: -0.1700

Data Index: 5714912 (Open Web Text)

Max Activating Token Index: 673

Text #13

Max Range: 4.2755. Min Range: -4.2755

Max Act: 3.8907. Min Act: -0.1698

Data Index: 651215 (Open Web Text)

Max Activating Token Index: 958

Text #14

Max Range: 4.2755. Min Range: -4.2755

Max Act: 3.9135. Min Act: -0.1700

Data Index: 4897026 (Open Web Text)

Max Activating Token Index: 265

Text #15

Max Range: 4.2755. Min Range: -4.2755

Max Act: 3.8721. Min Act: -0.1688

Data Index: 972197 (Open Web Text)

Max Activating Token Index: 785

Text #16

Max Range: 4.2755. Min Range: -4.2755

Max Act: 3.8957. Min Act: -0.1700

Data Index: 1402362 (Open Web Text)

Max Activating Token Index: 206

Text #17

Max Range: 4.2755. Min Range: -4.2755

Max Act: 3.8930. Min Act: -0.1700

Data Index: 5404259 (Open Web Text)

Max Activating Token Index: 226

Text #18

Max Range: 4.2755. Min Range: -4.2755

Max Act: 3.8644. Min Act: -0.1700

Data Index: 3428752 (Open Web Text)

Max Activating Token Index: 425

Text #19

Max Range: 4.2755. Min Range: -4.2755

Max Act: 3.8457. Min Act: -0.1700

Data Index: 1719380 (Open Web Text)

Max Activating Token Index: 745