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

Dataset: Open Web Text

Neuron 2661 in Layer 4

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: 2.2252. Min Range: -2.2252

Max Act: 2.2252. Min Act: -0.1700

Data Index: 3844019 (Open Web Text)

Max Activating Token Index: 94

Text #1

Max Range: 2.2252. Min Range: -2.2252

Max Act: 2.2024. Min Act: -0.1700

Data Index: 6878064 (Open Web Text)

Max Activating Token Index: 635

Text #2

Max Range: 2.2252. Min Range: -2.2252

Max Act: 2.1938. Min Act: -0.1700

Data Index: 7565123 (Open Web Text)

Max Activating Token Index: 141

Text #3

Max Range: 2.2252. Min Range: -2.2252

Max Act: 2.1568. Min Act: -0.1700

Data Index: 1063713 (Open Web Text)

Max Activating Token Index: 469

Text #4

Max Range: 2.2252. Min Range: -2.2252

Max Act: 2.1625. Min Act: -0.1700

Data Index: 7554070 (Open Web Text)

Max Activating Token Index: 506

Text #5

Max Range: 2.2252. Min Range: -2.2252

Max Act: 2.1674. Min Act: -0.1700

Data Index: 5555962 (Open Web Text)

Max Activating Token Index: 353

Text #6

Max Range: 2.2252. Min Range: -2.2252

Max Act: 2.1470. Min Act: -0.1700

Data Index: 5714180 (Open Web Text)

Max Activating Token Index: 800

Text #7

Max Range: 2.2252. Min Range: -2.2252

Max Act: 2.1323. Min Act: -0.1700

Data Index: 2704252 (Open Web Text)

Max Activating Token Index: 947

Text #8

Max Range: 2.2252. Min Range: -2.2252

Max Act: 2.1542. Min Act: -0.1700

Data Index: 3240606 (Open Web Text)

Max Activating Token Index: 69

Text #9

Max Range: 2.2252. Min Range: -2.2252

Max Act: 2.1219. Min Act: -0.1700

Data Index: 8327292 (Open Web Text)

Max Activating Token Index: 883

Text #10

Max Range: 2.2252. Min Range: -2.2252

Max Act: 2.1331. Min Act: -0.1700

Data Index: 6407548 (Open Web Text)

Max Activating Token Index: 51

Text #11

Max Range: 2.2252. Min Range: -2.2252

Max Act: 2.1365. Min Act: -0.1700

Data Index: 3022150 (Open Web Text)

Max Activating Token Index: 459

Text #12

Max Range: 2.2252. Min Range: -2.2252

Max Act: 2.1296. Min Act: -0.1700

Data Index: 433244 (Open Web Text)

Max Activating Token Index: 316

Text #13

Max Range: 2.2252. Min Range: -2.2252

Max Act: 2.1441. Min Act: -0.1700

Data Index: 2157020 (Open Web Text)

Max Activating Token Index: 62

Text #14

Max Range: 2.2252. Min Range: -2.2252

Max Act: 2.1399. Min Act: -0.1700

Data Index: 5431228 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 2.2252. Min Range: -2.2252

Max Act: 2.1267. Min Act: -0.1700

Data Index: 836066 (Open Web Text)

Max Activating Token Index: 1011

Text #16

Max Range: 2.2252. Min Range: -2.2252

Max Act: 2.1399. Min Act: -0.1700

Data Index: 5134792 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 2.2252. Min Range: -2.2252

Max Act: 2.1333. Min Act: -0.1700

Data Index: 4965688 (Open Web Text)

Max Activating Token Index: 35

Text #18

Max Range: 2.2252. Min Range: -2.2252

Max Act: 2.1235. Min Act: -0.1700

Data Index: 7009952 (Open Web Text)

Max Activating Token Index: 453

Text #19

Max Range: 2.2252. Min Range: -2.2252

Max Act: 2.1399. Min Act: -0.1700

Data Index: 493113 (Open Web Text)

Max Activating Token Index: 4