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

Dataset: Open Web Text

Neuron 1553 in Layer 3

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: 4.4478. Min Range: -4.4478

Max Act: 4.3952. Min Act: -0.1700

Data Index: 4228639 (Open Web Text)

Max Activating Token Index: 964

Text #1

Max Range: 4.4478. Min Range: -4.4478

Max Act: 4.4478. Min Act: -0.1700

Data Index: 3588934 (Open Web Text)

Max Activating Token Index: 620

Text #2

Max Range: 4.4478. Min Range: -4.4478

Max Act: 4.4463. Min Act: -0.1700

Data Index: 7580175 (Open Web Text)

Max Activating Token Index: 820

Text #3

Max Range: 4.4478. Min Range: -4.4478

Max Act: 4.4204. Min Act: -0.1700

Data Index: 5088116 (Open Web Text)

Max Activating Token Index: 508

Text #4

Max Range: 4.4478. Min Range: -4.4478

Max Act: 4.4314. Min Act: -0.1700

Data Index: 6672065 (Open Web Text)

Max Activating Token Index: 580

Text #5

Max Range: 4.4478. Min Range: -4.4478

Max Act: 4.4278. Min Act: -0.1700

Data Index: 2629478 (Open Web Text)

Max Activating Token Index: 442

Text #6

Max Range: 4.4478. Min Range: -4.4478

Max Act: 4.4449. Min Act: -0.1700

Data Index: 5599975 (Open Web Text)

Max Activating Token Index: 343

Text #7

Max Range: 4.4478. Min Range: -4.4478

Max Act: 4.3972. Min Act: -0.1700

Data Index: 5411934 (Open Web Text)

Max Activating Token Index: 115

Text #8

Max Range: 4.4478. Min Range: -4.4478

Max Act: 4.4232. Min Act: -0.1700

Data Index: 195606 (Open Web Text)

Max Activating Token Index: 621

Text #9

Max Range: 4.4478. Min Range: -4.4478

Max Act: 4.3701. Min Act: -0.1700

Data Index: 6683075 (Open Web Text)

Max Activating Token Index: 407

Text #10

Max Range: 4.4478. Min Range: -4.4478

Max Act: 4.4148. Min Act: -0.1700

Data Index: 5329928 (Open Web Text)

Max Activating Token Index: 367

Text #11

Max Range: 4.4478. Min Range: -4.4478

Max Act: 4.3587. Min Act: -0.1700

Data Index: 6399317 (Open Web Text)

Max Activating Token Index: 463

Text #12

Max Range: 4.4478. Min Range: -4.4478

Max Act: 4.3453. Min Act: -0.1700

Data Index: 6470859 (Open Web Text)

Max Activating Token Index: 80

Text #13

Max Range: 4.4478. Min Range: -4.4478

Max Act: 4.3377. Min Act: -0.1700

Data Index: 2455766 (Open Web Text)

Max Activating Token Index: 718

Text #14

Max Range: 4.4478. Min Range: -4.4478

Max Act: 4.3773. Min Act: -0.1700

Data Index: 3930112 (Open Web Text)

Max Activating Token Index: 650

Text #15

Max Range: 4.4478. Min Range: -4.4478

Max Act: 4.3588. Min Act: -0.1700

Data Index: 251451 (Open Web Text)

Max Activating Token Index: 284

Text #16

Max Range: 4.4478. Min Range: -4.4478

Max Act: 4.3742. Min Act: -0.1700

Data Index: 4003047 (Open Web Text)

Max Activating Token Index: 231

Text #17

Max Range: 4.4478. Min Range: -4.4478

Max Act: 4.3936. Min Act: -0.1700

Data Index: 3876876 (Open Web Text)

Max Activating Token Index: 600

Text #18

Max Range: 4.4478. Min Range: -4.4478

Max Act: 4.3366. Min Act: -0.1700

Data Index: 563651 (Open Web Text)

Max Activating Token Index: 433

Text #19

Max Range: 4.4478. Min Range: -4.4478

Max Act: 4.3522. Min Act: -0.1700

Data Index: 626754 (Open Web Text)

Max Activating Token Index: 362