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

Dataset: Open Web Text

Neuron 1335 in Layer 2

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: 3.0789. Min Range: -3.0789

Max Act: 3.0789. Min Act: -0.1700

Data Index: 5623442 (Open Web Text)

Max Activating Token Index: 312

Text #1

Max Range: 3.0789. Min Range: -3.0789

Max Act: 3.0561. Min Act: -0.1700

Data Index: 4186241 (Open Web Text)

Max Activating Token Index: 20

Text #2

Max Range: 3.0789. Min Range: -3.0789

Max Act: 3.0316. Min Act: -0.1700

Data Index: 8708951 (Open Web Text)

Max Activating Token Index: 492

Text #3

Max Range: 3.0789. Min Range: -3.0789

Max Act: 2.9983. Min Act: -0.1700

Data Index: 4285690 (Open Web Text)

Max Activating Token Index: 478

Text #4

Max Range: 3.0789. Min Range: -3.0789

Max Act: 2.9836. Min Act: -0.1700

Data Index: 5939416 (Open Web Text)

Max Activating Token Index: 18

Text #5

Max Range: 3.0789. Min Range: -3.0789

Max Act: 2.9745. Min Act: -0.1700

Data Index: 362392 (Open Web Text)

Max Activating Token Index: 17

Text #6

Max Range: 3.0789. Min Range: -3.0789

Max Act: 2.9455. Min Act: -0.1700

Data Index: 8600782 (Open Web Text)

Max Activating Token Index: 506

Text #7

Max Range: 3.0789. Min Range: -3.0789

Max Act: 2.9462. Min Act: -0.1700

Data Index: 7206862 (Open Web Text)

Max Activating Token Index: 786

Text #8

Max Range: 3.0789. Min Range: -3.0789

Max Act: 2.9505. Min Act: -0.1700

Data Index: 1975391 (Open Web Text)

Max Activating Token Index: 658

Text #9

Max Range: 3.0789. Min Range: -3.0789

Max Act: 2.9460. Min Act: -0.1700

Data Index: 7918743 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.0789. Min Range: -3.0789

Max Act: 2.9281. Min Act: -0.1700

Data Index: 7147516 (Open Web Text)

Max Activating Token Index: 929

Text #11

Max Range: 3.0789. Min Range: -3.0789

Max Act: 2.9398. Min Act: -0.1700

Data Index: 3186463 (Open Web Text)

Max Activating Token Index: 951

Text #12

Max Range: 3.0789. Min Range: -3.0789

Max Act: 2.9365. Min Act: -0.1700

Data Index: 6540401 (Open Web Text)

Max Activating Token Index: 576

Text #13

Max Range: 3.0789. Min Range: -3.0789

Max Act: 2.9224. Min Act: -0.1700

Data Index: 5412032 (Open Web Text)

Max Activating Token Index: 346

Text #14

Max Range: 3.0789. Min Range: -3.0789

Max Act: 2.9211. Min Act: -0.1700

Data Index: 4846630 (Open Web Text)

Max Activating Token Index: 12

Text #15

Max Range: 3.0789. Min Range: -3.0789

Max Act: 2.9213. Min Act: -0.1700

Data Index: 7647164 (Open Web Text)

Max Activating Token Index: 108

Text #16

Max Range: 3.0789. Min Range: -3.0789

Max Act: 2.8978. Min Act: -0.1700

Data Index: 2399203 (Open Web Text)

Max Activating Token Index: 535

Text #17

Max Range: 3.0789. Min Range: -3.0789

Max Act: 2.9048. Min Act: -0.1700

Data Index: 245102 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 3.0789. Min Range: -3.0789

Max Act: 2.9137. Min Act: -0.1700

Data Index: 6990685 (Open Web Text)

Max Activating Token Index: 10

Text #19

Max Range: 3.0789. Min Range: -3.0789

Max Act: 2.9168. Min Act: -0.1700

Data Index: 812518 (Open Web Text)

Max Activating Token Index: 36