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

Dataset: Open Web Text

Neuron 1222 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: 1.6502. Min Range: -1.6502

Max Act: 1.6502. Min Act: -0.1700

Data Index: 3238872 (Open Web Text)

Max Activating Token Index: 281

Text #1

Max Range: 1.6502. Min Range: -1.6502

Max Act: 1.6403. Min Act: -0.1700

Data Index: 2473264 (Open Web Text)

Max Activating Token Index: 517

Text #2

Max Range: 1.6502. Min Range: -1.6502

Max Act: 1.6387. Min Act: -0.1700

Data Index: 5047093 (Open Web Text)

Max Activating Token Index: 205

Text #3

Max Range: 1.6502. Min Range: -1.6502

Max Act: 1.6452. Min Act: -0.1700

Data Index: 4691820 (Open Web Text)

Max Activating Token Index: 498

Text #4

Max Range: 1.6502. Min Range: -1.6502

Max Act: 1.6322. Min Act: -0.1700

Data Index: 68224 (Open Web Text)

Max Activating Token Index: 752

Text #5

Max Range: 1.6502. Min Range: -1.6502

Max Act: 1.6320. Min Act: -0.1619

Data Index: 670700 (Open Web Text)

Max Activating Token Index: 465

Text #6

Max Range: 1.6502. Min Range: -1.6502

Max Act: 1.6395. Min Act: -0.1700

Data Index: 7542141 (Open Web Text)

Max Activating Token Index: 522

Text #7

Max Range: 1.6502. Min Range: -1.6502

Max Act: 1.6412. Min Act: -0.1700

Data Index: 5791772 (Open Web Text)

Max Activating Token Index: 256

Text #8

Max Range: 1.6502. Min Range: -1.6502

Max Act: 1.6355. Min Act: -0.1700

Data Index: 7456322 (Open Web Text)

Max Activating Token Index: 672

Text #9

Max Range: 1.6502. Min Range: -1.6502

Max Act: 1.6314. Min Act: -0.1700

Data Index: 3985658 (Open Web Text)

Max Activating Token Index: 546

Text #10

Max Range: 1.6502. Min Range: -1.6502

Max Act: 1.6187. Min Act: -0.1700

Data Index: 458200 (Open Web Text)

Max Activating Token Index: 974

Text #11

Max Range: 1.6502. Min Range: -1.6502

Max Act: 1.6107. Min Act: -0.1700

Data Index: 6005260 (Open Web Text)

Max Activating Token Index: 580

Text #12

Max Range: 1.6502. Min Range: -1.6502

Max Act: 1.6066. Min Act: -0.1700

Data Index: 8256037 (Open Web Text)

Max Activating Token Index: 255

Text #13

Max Range: 1.6502. Min Range: -1.6502

Max Act: 1.6044. Min Act: -0.1700

Data Index: 7332517 (Open Web Text)

Max Activating Token Index: 465

Text #14

Max Range: 1.6502. Min Range: -1.6502

Max Act: 1.6133. Min Act: -0.1700

Data Index: 7199396 (Open Web Text)

Max Activating Token Index: 429

Text #15

Max Range: 1.6502. Min Range: -1.6502

Max Act: 1.6162. Min Act: -0.1699

Data Index: 8051004 (Open Web Text)

Max Activating Token Index: 91

Text #16

Max Range: 1.6502. Min Range: -1.6502

Max Act: 1.6092. Min Act: -0.1700

Data Index: 7872346 (Open Web Text)

Max Activating Token Index: 566

Text #17

Max Range: 1.6502. Min Range: -1.6502

Max Act: 1.6096. Min Act: -0.1700

Data Index: 1381572 (Open Web Text)

Max Activating Token Index: 509

Text #18

Max Range: 1.6502. Min Range: -1.6502

Max Act: 1.6004. Min Act: -0.1700

Data Index: 3022111 (Open Web Text)

Max Activating Token Index: 160

Text #19

Max Range: 1.6502. Min Range: -1.6502

Max Act: 1.6032. Min Act: -0.1700

Data Index: 7733135 (Open Web Text)

Max Activating Token Index: 235