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

Dataset: Open Web Text

Neuron 70 in Layer 4

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: 3.3551. Min Range: -3.3551

Max Act: 3.3551. Min Act: -0.1700

Data Index: 3600420 (Open Web Text)

Max Activating Token Index: 927

Text #1

Max Range: 3.3551. Min Range: -3.3551

Max Act: 3.3174. Min Act: -0.1700

Data Index: 7693797 (Open Web Text)

Max Activating Token Index: 301

Text #2

Max Range: 3.3551. Min Range: -3.3551

Max Act: 3.2422. Min Act: -0.1700

Data Index: 5140097 (Open Web Text)

Max Activating Token Index: 834

Text #3

Max Range: 3.3551. Min Range: -3.3551

Max Act: 3.2521. Min Act: -0.1700

Data Index: 7693800 (Open Web Text)

Max Activating Token Index: 241

Text #4

Max Range: 3.3551. Min Range: -3.3551

Max Act: 3.2395. Min Act: -0.1700

Data Index: 1894955 (Open Web Text)

Max Activating Token Index: 946

Text #5

Max Range: 3.3551. Min Range: -3.3551

Max Act: 3.1942. Min Act: -0.1700

Data Index: 3514592 (Open Web Text)

Max Activating Token Index: 737

Text #6

Max Range: 3.3551. Min Range: -3.3551

Max Act: 3.1881. Min Act: -0.1700

Data Index: 3953549 (Open Web Text)

Max Activating Token Index: 788

Text #7

Max Range: 3.3551. Min Range: -3.3551

Max Act: 3.1874. Min Act: -0.1700

Data Index: 3600421 (Open Web Text)

Max Activating Token Index: 356

Text #8

Max Range: 3.3551. Min Range: -3.3551

Max Act: 3.1475. Min Act: -0.1700

Data Index: 8019430 (Open Web Text)

Max Activating Token Index: 35

Text #9

Max Range: 3.3551. Min Range: -3.3551

Max Act: 3.1431. Min Act: -0.1700

Data Index: 2105864 (Open Web Text)

Max Activating Token Index: 605

Text #10

Max Range: 3.3551. Min Range: -3.3551

Max Act: 3.1673. Min Act: -0.1700

Data Index: 1271092 (Open Web Text)

Max Activating Token Index: 684

Text #11

Max Range: 3.3551. Min Range: -3.3551

Max Act: 3.1385. Min Act: -0.1700

Data Index: 2875438 (Open Web Text)

Max Activating Token Index: 473

Text #12

Max Range: 3.3551. Min Range: -3.3551

Max Act: 3.1228. Min Act: -0.1700

Data Index: 7254772 (Open Web Text)

Max Activating Token Index: 421

Text #13

Max Range: 3.3551. Min Range: -3.3551

Max Act: 3.1314. Min Act: -0.1700

Data Index: 3051429 (Open Web Text)

Max Activating Token Index: 629

Text #14

Max Range: 3.3551. Min Range: -3.3551

Max Act: 3.1374. Min Act: -0.1700

Data Index: 4988300 (Open Web Text)

Max Activating Token Index: 424

Text #15

Max Range: 3.3551. Min Range: -3.3551

Max Act: 3.1157. Min Act: -0.1700

Data Index: 8396566 (Open Web Text)

Max Activating Token Index: 420

Text #16

Max Range: 3.3551. Min Range: -3.3551

Max Act: 3.0977. Min Act: -0.1700

Data Index: 2211349 (Open Web Text)

Max Activating Token Index: 856

Text #17

Max Range: 3.3551. Min Range: -3.3551

Max Act: 3.0744. Min Act: -0.1700

Data Index: 852180 (Open Web Text)

Max Activating Token Index: 616

Text #18

Max Range: 3.3551. Min Range: -3.3551

Max Act: 3.0269. Min Act: -0.1700

Data Index: 3663484 (Open Web Text)

Max Activating Token Index: 511

Text #19

Max Range: 3.3551. Min Range: -3.3551

Max Act: 3.0845. Min Act: -0.1700

Data Index: 646147 (Open Web Text)

Max Activating Token Index: 973