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

Dataset: Open Web Text

Neuron 2672 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: 4.0536. Min Range: -4.0536

Max Act: 4.0536. Min Act: -0.1700

Data Index: 810507 (Open Web Text)

Max Activating Token Index: 323

Text #1

Max Range: 4.0536. Min Range: -4.0536

Max Act: 4.0032. Min Act: -0.1700

Data Index: 7453270 (Open Web Text)

Max Activating Token Index: 474

Text #2

Max Range: 4.0536. Min Range: -4.0536

Max Act: 4.0269. Min Act: -0.1700

Data Index: 3926340 (Open Web Text)

Max Activating Token Index: 324

Text #3

Max Range: 4.0536. Min Range: -4.0536

Max Act: 4.0196. Min Act: -0.1700

Data Index: 5385127 (Open Web Text)

Max Activating Token Index: 498

Text #4

Max Range: 4.0536. Min Range: -4.0536

Max Act: 3.9706. Min Act: -0.1700

Data Index: 416606 (Open Web Text)

Max Activating Token Index: 576

Text #5

Max Range: 4.0536. Min Range: -4.0536

Max Act: 3.9914. Min Act: -0.1700

Data Index: 823967 (Open Web Text)

Max Activating Token Index: 113

Text #6

Max Range: 4.0536. Min Range: -4.0536

Max Act: 3.9645. Min Act: -0.1700

Data Index: 8824740 (Open Web Text)

Max Activating Token Index: 754

Text #7

Max Range: 4.0536. Min Range: -4.0536

Max Act: 3.9438. Min Act: -0.1700

Data Index: 22152 (Open Web Text)

Max Activating Token Index: 687

Text #8

Max Range: 4.0536. Min Range: -4.0536

Max Act: 3.9332. Min Act: -0.1700

Data Index: 1705601 (Open Web Text)

Max Activating Token Index: 1007

Text #9

Max Range: 4.0536. Min Range: -4.0536

Max Act: 3.9300. Min Act: -0.1700

Data Index: 4544578 (Open Web Text)

Max Activating Token Index: 318

Text #10

Max Range: 4.0536. Min Range: -4.0536

Max Act: 3.9215. Min Act: -0.1700

Data Index: 8133028 (Open Web Text)

Max Activating Token Index: 152

Text #11

Max Range: 4.0536. Min Range: -4.0536

Max Act: 3.9307. Min Act: -0.1700

Data Index: 7336293 (Open Web Text)

Max Activating Token Index: 51

Text #12

Max Range: 4.0536. Min Range: -4.0536

Max Act: 3.9078. Min Act: -0.1700

Data Index: 3725414 (Open Web Text)

Max Activating Token Index: 720

Text #13

Max Range: 4.0536. Min Range: -4.0536

Max Act: 3.9237. Min Act: -0.1700

Data Index: 2638898 (Open Web Text)

Max Activating Token Index: 707

Text #14

Max Range: 4.0536. Min Range: -4.0536

Max Act: 3.8817. Min Act: -0.1700

Data Index: 4140284 (Open Web Text)

Max Activating Token Index: 321

Text #15

Max Range: 4.0536. Min Range: -4.0536

Max Act: 3.8818. Min Act: -0.1700

Data Index: 214690 (Open Web Text)

Max Activating Token Index: 745

Text #16

Max Range: 4.0536. Min Range: -4.0536

Max Act: 3.8945. Min Act: -0.1700

Data Index: 6113058 (Open Web Text)

Max Activating Token Index: 121

Text #17

Max Range: 4.0536. Min Range: -4.0536

Max Act: 3.9027. Min Act: -0.1699

Data Index: 4015963 (Open Web Text)

Max Activating Token Index: 122

Text #18

Max Range: 4.0536. Min Range: -4.0536

Max Act: 3.9002. Min Act: -0.1700

Data Index: 2305164 (Open Web Text)

Max Activating Token Index: 557

Text #19

Max Range: 4.0536. Min Range: -4.0536

Max Act: 3.8950. Min Act: -0.1700

Data Index: 7392872 (Open Web Text)

Max Activating Token Index: 987