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

Dataset: Open Web Text

Neuron 2046 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: 3.4153. Min Range: -3.4153

Max Act: 3.4153. Min Act: -0.1700

Data Index: 5609541 (Open Web Text)

Max Activating Token Index: 383

Text #1

Max Range: 3.4153. Min Range: -3.4153

Max Act: 3.3735. Min Act: -0.1700

Data Index: 6386735 (Open Web Text)

Max Activating Token Index: 12

Text #2

Max Range: 3.4153. Min Range: -3.4153

Max Act: 3.2620. Min Act: -0.1700

Data Index: 5492556 (Open Web Text)

Max Activating Token Index: 807

Text #3

Max Range: 3.4153. Min Range: -3.4153

Max Act: 3.2630. Min Act: -0.1700

Data Index: 5563042 (Open Web Text)

Max Activating Token Index: 377

Text #4

Max Range: 3.4153. Min Range: -3.4153

Max Act: 3.2487. Min Act: -0.1700

Data Index: 1815954 (Open Web Text)

Max Activating Token Index: 11

Text #5

Max Range: 3.4153. Min Range: -3.4153

Max Act: 3.2267. Min Act: -0.1700

Data Index: 8592087 (Open Web Text)

Max Activating Token Index: 395

Text #6

Max Range: 3.4153. Min Range: -3.4153

Max Act: 3.2516. Min Act: -0.1700

Data Index: 1844435 (Open Web Text)

Max Activating Token Index: 606

Text #7

Max Range: 3.4153. Min Range: -3.4153

Max Act: 3.2272. Min Act: -0.1700

Data Index: 4330804 (Open Web Text)

Max Activating Token Index: 600

Text #8

Max Range: 3.4153. Min Range: -3.4153

Max Act: 3.2663. Min Act: -0.1700

Data Index: 6191284 (Open Web Text)

Max Activating Token Index: 575

Text #9

Max Range: 3.4153. Min Range: -3.4153

Max Act: 3.2500. Min Act: -0.1700

Data Index: 4330807 (Open Web Text)

Max Activating Token Index: 290

Text #10

Max Range: 3.4153. Min Range: -3.4153

Max Act: 3.2447. Min Act: -0.1700

Data Index: 8306255 (Open Web Text)

Max Activating Token Index: 631

Text #11

Max Range: 3.4153. Min Range: -3.4153

Max Act: 3.1655. Min Act: -0.1700

Data Index: 5660462 (Open Web Text)

Max Activating Token Index: 988

Text #12

Max Range: 3.4153. Min Range: -3.4153

Max Act: 3.1991. Min Act: -0.1700

Data Index: 2398159 (Open Web Text)

Max Activating Token Index: 77

Text #13

Max Range: 3.4153. Min Range: -3.4153

Max Act: 3.2184. Min Act: -0.1700

Data Index: 442347 (Open Web Text)

Max Activating Token Index: 453

Text #14

Max Range: 3.4153. Min Range: -3.4153

Max Act: 3.2227. Min Act: -0.1700

Data Index: 2686618 (Open Web Text)

Max Activating Token Index: 933

Text #15

Max Range: 3.4153. Min Range: -3.4153

Max Act: 3.2026. Min Act: -0.1700

Data Index: 5694689 (Open Web Text)

Max Activating Token Index: 820

Text #16

Max Range: 3.4153. Min Range: -3.4153

Max Act: 3.1676. Min Act: -0.1700

Data Index: 1289630 (Open Web Text)

Max Activating Token Index: 677

Text #17

Max Range: 3.4153. Min Range: -3.4153

Max Act: 3.1989. Min Act: -0.1700

Data Index: 3925544 (Open Web Text)

Max Activating Token Index: 645

Text #18

Max Range: 3.4153. Min Range: -3.4153

Max Act: 3.1629. Min Act: -0.1700

Data Index: 3955124 (Open Web Text)

Max Activating Token Index: 730

Text #19

Max Range: 3.4153. Min Range: -3.4153

Max Act: 3.1968. Min Act: -0.1700

Data Index: 3760477 (Open Web Text)

Max Activating Token Index: 279