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

Dataset: Open Web Text

Neuron 1587 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: 4.0613. Min Range: -4.0613

Max Act: 4.0613. Min Act: -0.1700

Data Index: 1239281 (Open Web Text)

Max Activating Token Index: 396

Text #1

Max Range: 4.0613. Min Range: -4.0613

Max Act: 3.9492. Min Act: -0.1700

Data Index: 4344063 (Open Web Text)

Max Activating Token Index: 632

Text #2

Max Range: 4.0613. Min Range: -4.0613

Max Act: 3.8467. Min Act: -0.1700

Data Index: 7244028 (Open Web Text)

Max Activating Token Index: 379

Text #3

Max Range: 4.0613. Min Range: -4.0613

Max Act: 3.9069. Min Act: -0.1700

Data Index: 3706643 (Open Web Text)

Max Activating Token Index: 328

Text #4

Max Range: 4.0613. Min Range: -4.0613

Max Act: 3.8473. Min Act: -0.1700

Data Index: 6060449 (Open Web Text)

Max Activating Token Index: 450

Text #5

Max Range: 4.0613. Min Range: -4.0613

Max Act: 3.7302. Min Act: -0.1700

Data Index: 5951290 (Open Web Text)

Max Activating Token Index: 355

Text #6

Max Range: 4.0613. Min Range: -4.0613

Max Act: 3.8983. Min Act: -0.1700

Data Index: 8132180 (Open Web Text)

Max Activating Token Index: 908

Text #7

Max Range: 4.0613. Min Range: -4.0613

Max Act: 3.7851. Min Act: -0.1700

Data Index: 4152195 (Open Web Text)

Max Activating Token Index: 446

Text #8

Max Range: 4.0613. Min Range: -4.0613

Max Act: 3.8996. Min Act: -0.1700

Data Index: 4117719 (Open Web Text)

Max Activating Token Index: 760

Text #9

Max Range: 4.0613. Min Range: -4.0613

Max Act: 3.7060. Min Act: -0.1700

Data Index: 6682047 (Open Web Text)

Max Activating Token Index: 418

Text #10

Max Range: 4.0613. Min Range: -4.0613

Max Act: 3.8146. Min Act: -0.1700

Data Index: 7956622 (Open Web Text)

Max Activating Token Index: 521

Text #11

Max Range: 4.0613. Min Range: -4.0613

Max Act: 3.8425. Min Act: -0.1700

Data Index: 7311346 (Open Web Text)

Max Activating Token Index: 362

Text #12

Max Range: 4.0613. Min Range: -4.0613

Max Act: 3.8112. Min Act: -0.1700

Data Index: 2968996 (Open Web Text)

Max Activating Token Index: 392

Text #13

Max Range: 4.0613. Min Range: -4.0613

Max Act: 3.8881. Min Act: -0.1700

Data Index: 3666236 (Open Web Text)

Max Activating Token Index: 217

Text #14

Max Range: 4.0613. Min Range: -4.0613

Max Act: 3.7157. Min Act: -0.1700

Data Index: 2434011 (Open Web Text)

Max Activating Token Index: 931

Text #15

Max Range: 4.0613. Min Range: -4.0613

Max Act: 3.6818. Min Act: -0.1700

Data Index: 6317114 (Open Web Text)

Max Activating Token Index: 388

Text #16

Max Range: 4.0613. Min Range: -4.0613

Max Act: 3.7667. Min Act: -0.1700

Data Index: 2616476 (Open Web Text)

Max Activating Token Index: 368

Text #17

Max Range: 4.0613. Min Range: -4.0613

Max Act: 3.5311. Min Act: -0.1700

Data Index: 384790 (Open Web Text)

Max Activating Token Index: 561

Text #18

Max Range: 4.0613. Min Range: -4.0613

Max Act: 3.8472. Min Act: -0.1700

Data Index: 2785661 (Open Web Text)

Max Activating Token Index: 791

Text #19

Max Range: 4.0613. Min Range: -4.0613

Max Act: 3.7342. Min Act: -0.1700

Data Index: 1206558 (Open Web Text)

Max Activating Token Index: 415