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

Dataset: Open Web Text

Neuron 51 in Layer 3

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: 1.9994. Min Range: -1.9994

Max Act: 1.9682. Min Act: -0.1700

Data Index: 5968005 (Open Web Text)

Max Activating Token Index: 542

Text #1

Max Range: 1.9994. Min Range: -1.9994

Max Act: 1.9898. Min Act: -0.1700

Data Index: 8538574 (Open Web Text)

Max Activating Token Index: 369

Text #2

Max Range: 1.9994. Min Range: -1.9994

Max Act: 1.9994. Min Act: -0.1700

Data Index: 2482430 (Open Web Text)

Max Activating Token Index: 370

Text #3

Max Range: 1.9994. Min Range: -1.9994

Max Act: 1.9610. Min Act: -0.1700

Data Index: 2367240 (Open Web Text)

Max Activating Token Index: 489

Text #4

Max Range: 1.9994. Min Range: -1.9994

Max Act: 1.9822. Min Act: -0.1695

Data Index: 7547302 (Open Web Text)

Max Activating Token Index: 886

Text #5

Max Range: 1.9994. Min Range: -1.9994

Max Act: 1.9420. Min Act: -0.1700

Data Index: 2602781 (Open Web Text)

Max Activating Token Index: 239

Text #6

Max Range: 1.9994. Min Range: -1.9994

Max Act: 1.9533. Min Act: -0.1700

Data Index: 2634722 (Open Web Text)

Max Activating Token Index: 119

Text #7

Max Range: 1.9994. Min Range: -1.9994

Max Act: 1.9485. Min Act: -0.1700

Data Index: 2263380 (Open Web Text)

Max Activating Token Index: 117

Text #8

Max Range: 1.9994. Min Range: -1.9994

Max Act: 1.9535. Min Act: -0.1700

Data Index: 4276920 (Open Web Text)

Max Activating Token Index: 843

Text #9

Max Range: 1.9994. Min Range: -1.9994

Max Act: 1.9611. Min Act: -0.1700

Data Index: 6350533 (Open Web Text)

Max Activating Token Index: 1001

Text #10

Max Range: 1.9994. Min Range: -1.9994

Max Act: 1.9375. Min Act: -0.1700

Data Index: 292778 (Open Web Text)

Max Activating Token Index: 884

Text #11

Max Range: 1.9994. Min Range: -1.9994

Max Act: 1.9409. Min Act: -0.1700

Data Index: 6642417 (Open Web Text)

Max Activating Token Index: 547

Text #12

Max Range: 1.9994. Min Range: -1.9994

Max Act: 1.9190. Min Act: -0.1700

Data Index: 5931736 (Open Web Text)

Max Activating Token Index: 967

Text #13

Max Range: 1.9994. Min Range: -1.9994

Max Act: 1.9180. Min Act: -0.1700

Data Index: 1293955 (Open Web Text)

Max Activating Token Index: 798

Text #14

Max Range: 1.9994. Min Range: -1.9994

Max Act: 1.9231. Min Act: -0.1700

Data Index: 3843886 (Open Web Text)

Max Activating Token Index: 276

Text #15

Max Range: 1.9994. Min Range: -1.9994

Max Act: 1.9263. Min Act: -0.1700

Data Index: 8467628 (Open Web Text)

Max Activating Token Index: 265

Text #16

Max Range: 1.9994. Min Range: -1.9994

Max Act: 1.9289. Min Act: -0.1700

Data Index: 8288911 (Open Web Text)

Max Activating Token Index: 544

Text #17

Max Range: 1.9994. Min Range: -1.9994

Max Act: 1.9136. Min Act: -0.1700

Data Index: 7987104 (Open Web Text)

Max Activating Token Index: 996

Text #18

Max Range: 1.9994. Min Range: -1.9994

Max Act: 1.9450. Min Act: -0.1700

Data Index: 7229897 (Open Web Text)

Max Activating Token Index: 519

Text #19

Max Range: 1.9994. Min Range: -1.9994

Max Act: 1.9307. Min Act: -0.1700

Data Index: 3039003 (Open Web Text)

Max Activating Token Index: 197