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

Dataset: Open Web Text

Neuron 1991 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: 3.9343. Min Range: -3.9343

Max Act: 3.9343. Min Act: -0.1700

Data Index: 4619421 (Open Web Text)

Max Activating Token Index: 94

Text #1

Max Range: 3.9343. Min Range: -3.9343

Max Act: 3.8653. Min Act: -0.1700

Data Index: 1130496 (Open Web Text)

Max Activating Token Index: 861

Text #2

Max Range: 3.9343. Min Range: -3.9343

Max Act: 3.8737. Min Act: -0.1700

Data Index: 8005484 (Open Web Text)

Max Activating Token Index: 681

Text #3

Max Range: 3.9343. Min Range: -3.9343

Max Act: 3.8155. Min Act: -0.1700

Data Index: 5187530 (Open Web Text)

Max Activating Token Index: 369

Text #4

Max Range: 3.9343. Min Range: -3.9343

Max Act: 3.8353. Min Act: -0.1700

Data Index: 134780 (Open Web Text)

Max Activating Token Index: 266

Text #5

Max Range: 3.9343. Min Range: -3.9343

Max Act: 3.8022. Min Act: -0.1700

Data Index: 8703893 (Open Web Text)

Max Activating Token Index: 453

Text #6

Max Range: 3.9343. Min Range: -3.9343

Max Act: 3.7692. Min Act: -0.1700

Data Index: 1009932 (Open Web Text)

Max Activating Token Index: 79

Text #7

Max Range: 3.9343. Min Range: -3.9343

Max Act: 3.7369. Min Act: -0.1700

Data Index: 3627269 (Open Web Text)

Max Activating Token Index: 269

Text #8

Max Range: 3.9343. Min Range: -3.9343

Max Act: 3.7407. Min Act: -0.1700

Data Index: 3908895 (Open Web Text)

Max Activating Token Index: 273

Text #9

Max Range: 3.9343. Min Range: -3.9343

Max Act: 3.7423. Min Act: -0.1700

Data Index: 14348 (Open Web Text)

Max Activating Token Index: 492

Text #10

Max Range: 3.9343. Min Range: -3.9343

Max Act: 3.7575. Min Act: -0.1700

Data Index: 5872875 (Open Web Text)

Max Activating Token Index: 166

Text #11

Max Range: 3.9343. Min Range: -3.9343

Max Act: 3.7778. Min Act: -0.1700

Data Index: 1616175 (Open Web Text)

Max Activating Token Index: 150

Text #12

Max Range: 3.9343. Min Range: -3.9343

Max Act: 3.7741. Min Act: -0.1700

Data Index: 1287887 (Open Web Text)

Max Activating Token Index: 580

Text #13

Max Range: 3.9343. Min Range: -3.9343

Max Act: 3.7478. Min Act: -0.1700

Data Index: 2209329 (Open Web Text)

Max Activating Token Index: 453

Text #14

Max Range: 3.9343. Min Range: -3.9343

Max Act: 3.7597. Min Act: -0.1700

Data Index: 2563201 (Open Web Text)

Max Activating Token Index: 398

Text #15

Max Range: 3.9343. Min Range: -3.9343

Max Act: 3.7692. Min Act: -0.1700

Data Index: 3200427 (Open Web Text)

Max Activating Token Index: 65

Text #16

Max Range: 3.9343. Min Range: -3.9343

Max Act: 3.7446. Min Act: -0.1700

Data Index: 4792000 (Open Web Text)

Max Activating Token Index: 552

Text #17

Max Range: 3.9343. Min Range: -3.9343

Max Act: 3.6945. Min Act: -0.1700

Data Index: 4610577 (Open Web Text)

Max Activating Token Index: 487

Text #18

Max Range: 3.9343. Min Range: -3.9343

Max Act: 3.7476. Min Act: -0.1700

Data Index: 1167310 (Open Web Text)

Max Activating Token Index: 947

Text #19

Max Range: 3.9343. Min Range: -3.9343

Max Act: 3.7459. Min Act: -0.1700

Data Index: 4641787 (Open Web Text)

Max Activating Token Index: 959