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

Dataset: Open Web Text

Neuron 108 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: 2.5026. Min Range: -2.5026

Max Act: 2.4942. Min Act: -0.1700

Data Index: 1793675 (Open Web Text)

Max Activating Token Index: 22

Text #1

Max Range: 2.5026. Min Range: -2.5026

Max Act: 2.5026. Min Act: -0.1700

Data Index: 8428455 (Open Web Text)

Max Activating Token Index: 205

Text #2

Max Range: 2.5026. Min Range: -2.5026

Max Act: 2.4970. Min Act: -0.1700

Data Index: 4089652 (Open Web Text)

Max Activating Token Index: 423

Text #3

Max Range: 2.5026. Min Range: -2.5026

Max Act: 2.4713. Min Act: -0.1700

Data Index: 5103910 (Open Web Text)

Max Activating Token Index: 16

Text #4

Max Range: 2.5026. Min Range: -2.5026

Max Act: 2.4754. Min Act: -0.1700

Data Index: 7386830 (Open Web Text)

Max Activating Token Index: 590

Text #5

Max Range: 2.5026. Min Range: -2.5026

Max Act: 2.4626. Min Act: -0.1700

Data Index: 3902099 (Open Web Text)

Max Activating Token Index: 756

Text #6

Max Range: 2.5026. Min Range: -2.5026

Max Act: 2.4616. Min Act: -0.1700

Data Index: 1034740 (Open Web Text)

Max Activating Token Index: 16

Text #7

Max Range: 2.5026. Min Range: -2.5026

Max Act: 2.4624. Min Act: -0.1700

Data Index: 6983125 (Open Web Text)

Max Activating Token Index: 524

Text #8

Max Range: 2.5026. Min Range: -2.5026

Max Act: 2.4578. Min Act: -0.1700

Data Index: 8814251 (Open Web Text)

Max Activating Token Index: 535

Text #9

Max Range: 2.5026. Min Range: -2.5026

Max Act: 2.4722. Min Act: -0.1700

Data Index: 1442030 (Open Web Text)

Max Activating Token Index: 306

Text #10

Max Range: 2.5026. Min Range: -2.5026

Max Act: 2.4659. Min Act: -0.1700

Data Index: 5906393 (Open Web Text)

Max Activating Token Index: 819

Text #11

Max Range: 2.5026. Min Range: -2.5026

Max Act: 2.4572. Min Act: -0.1700

Data Index: 3803444 (Open Web Text)

Max Activating Token Index: 274

Text #12

Max Range: 2.5026. Min Range: -2.5026

Max Act: 2.4462. Min Act: -0.1700

Data Index: 4408871 (Open Web Text)

Max Activating Token Index: 569

Text #13

Max Range: 2.5026. Min Range: -2.5026

Max Act: 2.4548. Min Act: -0.1700

Data Index: 6291551 (Open Web Text)

Max Activating Token Index: 929

Text #14

Max Range: 2.5026. Min Range: -2.5026

Max Act: 2.4572. Min Act: -0.1700

Data Index: 3367660 (Open Web Text)

Max Activating Token Index: 520

Text #15

Max Range: 2.5026. Min Range: -2.5026

Max Act: 2.4476. Min Act: -0.1700

Data Index: 119998 (Open Web Text)

Max Activating Token Index: 879

Text #16

Max Range: 2.5026. Min Range: -2.5026

Max Act: 2.4572. Min Act: -0.1700

Data Index: 7321406 (Open Web Text)

Max Activating Token Index: 421

Text #17

Max Range: 2.5026. Min Range: -2.5026

Max Act: 2.4370. Min Act: -0.1700

Data Index: 2390271 (Open Web Text)

Max Activating Token Index: 284

Text #18

Max Range: 2.5026. Min Range: -2.5026

Max Act: 2.4334. Min Act: -0.1700

Data Index: 84802 (Open Web Text)

Max Activating Token Index: 238

Text #19

Max Range: 2.5026. Min Range: -2.5026

Max Act: 2.4297. Min Act: -0.1700

Data Index: 4382300 (Open Web Text)

Max Activating Token Index: 695