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

Dataset: Open Web Text

Neuron 867 in Layer 0

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: 1.3888. Min Range: -1.3888

Max Act: 1.3888. Min Act: -0.1335

Data Index: 589481 (Open Web Text)

Max Activating Token Index: 125

Text #1

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.3775. Min Act: -0.1335

Data Index: 3123340 (Open Web Text)

Max Activating Token Index: 369

Text #2

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.3699. Min Act: -0.1335

Data Index: 4544566 (Open Web Text)

Max Activating Token Index: 923

Text #3

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.3717. Min Act: -0.1335

Data Index: 3485566 (Open Web Text)

Max Activating Token Index: 334

Text #4

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.3656. Min Act: -0.1335

Data Index: 1041539 (Open Web Text)

Max Activating Token Index: 502

Text #5

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.3656. Min Act: -0.1335

Data Index: 7969709 (Open Web Text)

Max Activating Token Index: 825

Text #6

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.3638. Min Act: -0.1335

Data Index: 3028990 (Open Web Text)

Max Activating Token Index: 402

Text #7

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.3456. Min Act: -0.1362

Data Index: 4803712 (Open Web Text)

Max Activating Token Index: 969

Text #8

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.3489. Min Act: -0.1335

Data Index: 2999585 (Open Web Text)

Max Activating Token Index: 144

Text #9

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.3422. Min Act: -0.1335

Data Index: 2289204 (Open Web Text)

Max Activating Token Index: 424

Text #10

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.3415. Min Act: -0.1335

Data Index: 6973767 (Open Web Text)

Max Activating Token Index: 300

Text #11

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.3400. Min Act: -0.1547

Data Index: 6875147 (Open Web Text)

Max Activating Token Index: 811

Text #12

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.3439. Min Act: -0.1470

Data Index: 760194 (Open Web Text)

Max Activating Token Index: 383

Text #13

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.3501. Min Act: -0.1335

Data Index: 7914362 (Open Web Text)

Max Activating Token Index: 536

Text #14

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.3293. Min Act: -0.1335

Data Index: 7490584 (Open Web Text)

Max Activating Token Index: 153

Text #15

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.3331. Min Act: -0.1335

Data Index: 3407257 (Open Web Text)

Max Activating Token Index: 495

Text #16

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.3384. Min Act: -0.1335

Data Index: 3589927 (Open Web Text)

Max Activating Token Index: 493

Text #17

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.3229. Min Act: -0.1335

Data Index: 5548117 (Open Web Text)

Max Activating Token Index: 856

Text #18

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.3380. Min Act: -0.1472

Data Index: 1424299 (Open Web Text)

Max Activating Token Index: 364

Text #19

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.3345. Min Act: -0.1528

Data Index: 5046028 (Open Web Text)

Max Activating Token Index: 553