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

Dataset: Open Web Text

Neuron 2965 in Layer 1

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: 3.8769. Min Range: -3.8769

Max Act: 3.8685. Min Act: -0.1616

Data Index: 6418251 (Open Web Text)

Max Activating Token Index: 206

Text #1

Max Range: 3.8769. Min Range: -3.8769

Max Act: 3.8769. Min Act: -0.1483

Data Index: 6418250 (Open Web Text)

Max Activating Token Index: 204

Text #2

Max Range: 3.8769. Min Range: -3.8769

Max Act: 3.5569. Min Act: -0.1700

Data Index: 5041336 (Open Web Text)

Max Activating Token Index: 374

Text #3

Max Range: 3.8769. Min Range: -3.8769

Max Act: 3.5719. Min Act: -0.1700

Data Index: 7319585 (Open Web Text)

Max Activating Token Index: 970

Text #4

Max Range: 3.8769. Min Range: -3.8769

Max Act: 3.5326. Min Act: -0.1700

Data Index: 8405042 (Open Web Text)

Max Activating Token Index: 396

Text #5

Max Range: 3.8769. Min Range: -3.8769

Max Act: 3.5549. Min Act: -0.1700

Data Index: 71565 (Open Web Text)

Max Activating Token Index: 392

Text #6

Max Range: 3.8769. Min Range: -3.8769

Max Act: 3.5000. Min Act: -0.1700

Data Index: 3140081 (Open Web Text)

Max Activating Token Index: 554

Text #7

Max Range: 3.8769. Min Range: -3.8769

Max Act: 3.4717. Min Act: -0.1700

Data Index: 7049329 (Open Web Text)

Max Activating Token Index: 385

Text #8

Max Range: 3.8769. Min Range: -3.8769

Max Act: 3.4952. Min Act: -0.1700

Data Index: 1249387 (Open Web Text)

Max Activating Token Index: 398

Text #9

Max Range: 3.8769. Min Range: -3.8769

Max Act: 3.5087. Min Act: -0.1700

Data Index: 4344332 (Open Web Text)

Max Activating Token Index: 320

Text #10

Max Range: 3.8769. Min Range: -3.8769

Max Act: 3.4812. Min Act: -0.1700

Data Index: 4726191 (Open Web Text)

Max Activating Token Index: 409

Text #11

Max Range: 3.8769. Min Range: -3.8769

Max Act: 3.4635. Min Act: -0.1700

Data Index: 6418252 (Open Web Text)

Max Activating Token Index: 108

Text #12

Max Range: 3.8769. Min Range: -3.8769

Max Act: 3.4526. Min Act: -0.1696

Data Index: 2717759 (Open Web Text)

Max Activating Token Index: 386

Text #13

Max Range: 3.8769. Min Range: -3.8769

Max Act: 3.4983. Min Act: -0.1700

Data Index: 1249385 (Open Web Text)

Max Activating Token Index: 397

Text #14

Max Range: 3.8769. Min Range: -3.8769

Max Act: 3.4752. Min Act: -0.1700

Data Index: 1249391 (Open Web Text)

Max Activating Token Index: 399

Text #15

Max Range: 3.8769. Min Range: -3.8769

Max Act: 3.4282. Min Act: -0.1700

Data Index: 1249398 (Open Web Text)

Max Activating Token Index: 397

Text #16

Max Range: 3.8769. Min Range: -3.8769

Max Act: 3.4093. Min Act: -0.1700

Data Index: 1249383 (Open Web Text)

Max Activating Token Index: 395

Text #17

Max Range: 3.8769. Min Range: -3.8769

Max Act: 3.4266. Min Act: -0.1700

Data Index: 5762206 (Open Web Text)

Max Activating Token Index: 382

Text #18

Max Range: 3.8769. Min Range: -3.8769

Max Act: 3.4062. Min Act: -0.1700

Data Index: 1249394 (Open Web Text)

Max Activating Token Index: 395

Text #19

Max Range: 3.8769. Min Range: -3.8769

Max Act: 3.4389. Min Act: -0.1700

Data Index: 527255 (Open Web Text)

Max Activating Token Index: 394