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

Dataset: Open Web Text

Neuron 912 in Layer 5

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: 5.2333. Min Range: -5.2333

Max Act: 5.2333. Min Act: -0.1700

Data Index: 2154265 (Open Web Text)

Max Activating Token Index: 500

Text #1

Max Range: 5.2333. Min Range: -5.2333

Max Act: 5.1701. Min Act: -0.1700

Data Index: 2441653 (Open Web Text)

Max Activating Token Index: 530

Text #2

Max Range: 5.2333. Min Range: -5.2333

Max Act: 5.1378. Min Act: -0.1700

Data Index: 3471839 (Open Web Text)

Max Activating Token Index: 523

Text #3

Max Range: 5.2333. Min Range: -5.2333

Max Act: 5.0223. Min Act: -0.1700

Data Index: 4556385 (Open Web Text)

Max Activating Token Index: 142

Text #4

Max Range: 5.2333. Min Range: -5.2333

Max Act: 5.0492. Min Act: -0.1700

Data Index: 162226 (Open Web Text)

Max Activating Token Index: 716

Text #5

Max Range: 5.2333. Min Range: -5.2333

Max Act: 4.9505. Min Act: -0.1700

Data Index: 5768434 (Open Web Text)

Max Activating Token Index: 620

Text #6

Max Range: 5.2333. Min Range: -5.2333

Max Act: 4.9740. Min Act: -0.1700

Data Index: 6666238 (Open Web Text)

Max Activating Token Index: 994

Text #7

Max Range: 5.2333. Min Range: -5.2333

Max Act: 4.9865. Min Act: -0.1700

Data Index: 8045453 (Open Web Text)

Max Activating Token Index: 784

Text #8

Max Range: 5.2333. Min Range: -5.2333

Max Act: 4.9374. Min Act: -0.1700

Data Index: 888405 (Open Web Text)

Max Activating Token Index: 847

Text #9

Max Range: 5.2333. Min Range: -5.2333

Max Act: 4.9590. Min Act: -0.1700

Data Index: 8034647 (Open Web Text)

Max Activating Token Index: 517

Text #10

Max Range: 5.2333. Min Range: -5.2333

Max Act: 4.9802. Min Act: -0.1700

Data Index: 4516312 (Open Web Text)

Max Activating Token Index: 574

Text #11

Max Range: 5.2333. Min Range: -5.2333

Max Act: 4.9465. Min Act: -0.1700

Data Index: 7167571 (Open Web Text)

Max Activating Token Index: 51

Text #12

Max Range: 5.2333. Min Range: -5.2333

Max Act: 4.9258. Min Act: -0.1700

Data Index: 2281612 (Open Web Text)

Max Activating Token Index: 292

Text #13

Max Range: 5.2333. Min Range: -5.2333

Max Act: 4.9174. Min Act: -0.1700

Data Index: 2141782 (Open Web Text)

Max Activating Token Index: 991

Text #14

Max Range: 5.2333. Min Range: -5.2333

Max Act: 4.9587. Min Act: -0.1700

Data Index: 6745754 (Open Web Text)

Max Activating Token Index: 371

Text #15

Max Range: 5.2333. Min Range: -5.2333

Max Act: 4.8989. Min Act: -0.1700

Data Index: 932207 (Open Web Text)

Max Activating Token Index: 966

Text #16

Max Range: 5.2333. Min Range: -5.2333

Max Act: 4.9326. Min Act: -0.1700

Data Index: 4259678 (Open Web Text)

Max Activating Token Index: 622

Text #17

Max Range: 5.2333. Min Range: -5.2333

Max Act: 4.9053. Min Act: -0.1700

Data Index: 8735871 (Open Web Text)

Max Activating Token Index: 781

Text #18

Max Range: 5.2333. Min Range: -5.2333

Max Act: 4.8929. Min Act: -0.1700

Data Index: 2803338 (Open Web Text)

Max Activating Token Index: 749

Text #19

Max Range: 5.2333. Min Range: -5.2333

Max Act: 4.8922. Min Act: -0.1700

Data Index: 5663322 (Open Web Text)

Max Activating Token Index: 30