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

Dataset: Open Web Text

Neuron 697 in Layer 1

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: 1.0156. Min Range: -1.0156

Max Act: 1.0156. Min Act: -0.1700

Data Index: 8315101 (Open Web Text)

Max Activating Token Index: 493

Text #1

Max Range: 1.0156. Min Range: -1.0156

Max Act: 0.8883. Min Act: -0.1700

Data Index: 4658327 (Open Web Text)

Max Activating Token Index: 496

Text #2

Max Range: 1.0156. Min Range: -1.0156

Max Act: 0.8778. Min Act: -0.1700

Data Index: 5028479 (Open Web Text)

Max Activating Token Index: 503

Text #3

Max Range: 1.0156. Min Range: -1.0156

Max Act: 0.8131. Min Act: -0.1700

Data Index: 7616533 (Open Web Text)

Max Activating Token Index: 461

Text #4

Max Range: 1.0156. Min Range: -1.0156

Max Act: 0.7955. Min Act: -0.1700

Data Index: 6606584 (Open Web Text)

Max Activating Token Index: 476

Text #5

Max Range: 1.0156. Min Range: -1.0156

Max Act: 0.7522. Min Act: -0.1700

Data Index: 2685775 (Open Web Text)

Max Activating Token Index: 496

Text #6

Max Range: 1.0156. Min Range: -1.0156

Max Act: 0.7437. Min Act: -0.1700

Data Index: 308050 (Open Web Text)

Max Activating Token Index: 489

Text #7

Max Range: 1.0156. Min Range: -1.0156

Max Act: 0.7098. Min Act: -0.1700

Data Index: 2770474 (Open Web Text)

Max Activating Token Index: 491

Text #8

Max Range: 1.0156. Min Range: -1.0156

Max Act: 0.6684. Min Act: -0.1700

Data Index: 524907 (Open Web Text)

Max Activating Token Index: 467

Text #9

Max Range: 1.0156. Min Range: -1.0156

Max Act: 0.6684. Min Act: -0.1700

Data Index: 1610857 (Open Web Text)

Max Activating Token Index: 470

Text #10

Max Range: 1.0156. Min Range: -1.0156

Max Act: 0.6403. Min Act: -0.1700

Data Index: 6311208 (Open Web Text)

Max Activating Token Index: 465

Text #11

Max Range: 1.0156. Min Range: -1.0156

Max Act: 0.6471. Min Act: -0.1700

Data Index: 8323843 (Open Web Text)

Max Activating Token Index: 459

Text #12

Max Range: 1.0156. Min Range: -1.0156

Max Act: 0.6179. Min Act: -0.1700

Data Index: 1315243 (Open Web Text)

Max Activating Token Index: 457

Text #13

Max Range: 1.0156. Min Range: -1.0156

Max Act: 0.6363. Min Act: -0.1700

Data Index: 5743591 (Open Web Text)

Max Activating Token Index: 500

Text #14

Max Range: 1.0156. Min Range: -1.0156

Max Act: 0.6304. Min Act: -0.1700

Data Index: 5022316 (Open Web Text)

Max Activating Token Index: 437

Text #15

Max Range: 1.0156. Min Range: -1.0156

Max Act: 0.6215. Min Act: -0.1700

Data Index: 5097004 (Open Web Text)

Max Activating Token Index: 475

Text #16

Max Range: 1.0156. Min Range: -1.0156

Max Act: 0.6170. Min Act: -0.1700

Data Index: 7266389 (Open Web Text)

Max Activating Token Index: 457

Text #17

Max Range: 1.0156. Min Range: -1.0156

Max Act: 0.6132. Min Act: -0.1700

Data Index: 3007350 (Open Web Text)

Max Activating Token Index: 464

Text #18

Max Range: 1.0156. Min Range: -1.0156

Max Act: 0.6122. Min Act: -0.1700

Data Index: 4919636 (Open Web Text)

Max Activating Token Index: 468

Text #19

Max Range: 1.0156. Min Range: -1.0156

Max Act: 0.5971. Min Act: -0.1700

Data Index: 4141563 (Open Web Text)

Max Activating Token Index: 454