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

Dataset: Open Web Text

Neuron 2689 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: 1.6406. Min Range: -1.6406

Max Act: 1.6406. Min Act: -0.1700

Data Index: 2020613 (Open Web Text)

Max Activating Token Index: 490

Text #1

Max Range: 1.6406. Min Range: -1.6406

Max Act: 1.6059. Min Act: -0.1700

Data Index: 614834 (Open Web Text)

Max Activating Token Index: 88

Text #2

Max Range: 1.6406. Min Range: -1.6406

Max Act: 1.5718. Min Act: -0.1700

Data Index: 4066707 (Open Web Text)

Max Activating Token Index: 453

Text #3

Max Range: 1.6406. Min Range: -1.6406

Max Act: 1.5770. Min Act: -0.1700

Data Index: 3196452 (Open Web Text)

Max Activating Token Index: 131

Text #4

Max Range: 1.6406. Min Range: -1.6406

Max Act: 1.5620. Min Act: -0.1700

Data Index: 2885290 (Open Web Text)

Max Activating Token Index: 460

Text #5

Max Range: 1.6406. Min Range: -1.6406

Max Act: 1.5451. Min Act: -0.1700

Data Index: 1224403 (Open Web Text)

Max Activating Token Index: 68

Text #6

Max Range: 1.6406. Min Range: -1.6406

Max Act: 1.5554. Min Act: -0.1700

Data Index: 5806313 (Open Web Text)

Max Activating Token Index: 64

Text #7

Max Range: 1.6406. Min Range: -1.6406

Max Act: 1.5601. Min Act: -0.1700

Data Index: 1962707 (Open Web Text)

Max Activating Token Index: 458

Text #8

Max Range: 1.6406. Min Range: -1.6406

Max Act: 1.5452. Min Act: -0.1700

Data Index: 3465902 (Open Web Text)

Max Activating Token Index: 18

Text #9

Max Range: 1.6406. Min Range: -1.6406

Max Act: 1.5451. Min Act: -0.1700

Data Index: 1236854 (Open Web Text)

Max Activating Token Index: 972

Text #10

Max Range: 1.6406. Min Range: -1.6406

Max Act: 1.5401. Min Act: -0.1700

Data Index: 5494897 (Open Web Text)

Max Activating Token Index: 29

Text #11

Max Range: 1.6406. Min Range: -1.6406

Max Act: 1.5317. Min Act: -0.1700

Data Index: 3136551 (Open Web Text)

Max Activating Token Index: 944

Text #12

Max Range: 1.6406. Min Range: -1.6406

Max Act: 1.5307. Min Act: -0.1700

Data Index: 807283 (Open Web Text)

Max Activating Token Index: 21

Text #13

Max Range: 1.6406. Min Range: -1.6406

Max Act: 1.5344. Min Act: -0.1700

Data Index: 906409 (Open Web Text)

Max Activating Token Index: 572

Text #14

Max Range: 1.6406. Min Range: -1.6406

Max Act: 1.5255. Min Act: -0.1700

Data Index: 3435453 (Open Web Text)

Max Activating Token Index: 288

Text #15

Max Range: 1.6406. Min Range: -1.6406

Max Act: 1.5186. Min Act: -0.1700

Data Index: 2959901 (Open Web Text)

Max Activating Token Index: 726

Text #16

Max Range: 1.6406. Min Range: -1.6406

Max Act: 1.5165. Min Act: -0.1700

Data Index: 4088163 (Open Web Text)

Max Activating Token Index: 371

Text #17

Max Range: 1.6406. Min Range: -1.6406

Max Act: 1.5177. Min Act: -0.1700

Data Index: 3907210 (Open Web Text)

Max Activating Token Index: 312

Text #18

Max Range: 1.6406. Min Range: -1.6406

Max Act: 1.5112. Min Act: -0.1700

Data Index: 6695496 (Open Web Text)

Max Activating Token Index: 131

Text #19

Max Range: 1.6406. Min Range: -1.6406

Max Act: 1.5115. Min Act: -0.1700

Data Index: 5402976 (Open Web Text)

Max Activating Token Index: 20