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

Dataset: Open Web Text

Neuron 614 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: 3.5736. Min Range: -3.5736

Max Act: 3.5736. Min Act: -0.1700

Data Index: 8373824 (Open Web Text)

Max Activating Token Index: 922

Text #1

Max Range: 3.5736. Min Range: -3.5736

Max Act: 3.5318. Min Act: -0.1700

Data Index: 5576574 (Open Web Text)

Max Activating Token Index: 118

Text #2

Max Range: 3.5736. Min Range: -3.5736

Max Act: 3.5441. Min Act: -0.1700

Data Index: 1430019 (Open Web Text)

Max Activating Token Index: 88

Text #3

Max Range: 3.5736. Min Range: -3.5736

Max Act: 3.5371. Min Act: -0.1700

Data Index: 4709266 (Open Web Text)

Max Activating Token Index: 342

Text #4

Max Range: 3.5736. Min Range: -3.5736

Max Act: 3.5577. Min Act: -0.1700

Data Index: 7819263 (Open Web Text)

Max Activating Token Index: 466

Text #5

Max Range: 3.5736. Min Range: -3.5736

Max Act: 3.4946. Min Act: -0.1700

Data Index: 8520731 (Open Web Text)

Max Activating Token Index: 1016

Text #6

Max Range: 3.5736. Min Range: -3.5736

Max Act: 3.5147. Min Act: -0.1700

Data Index: 635523 (Open Web Text)

Max Activating Token Index: 137

Text #7

Max Range: 3.5736. Min Range: -3.5736

Max Act: 3.4893. Min Act: -0.1700

Data Index: 3107532 (Open Web Text)

Max Activating Token Index: 336

Text #8

Max Range: 3.5736. Min Range: -3.5736

Max Act: 3.4795. Min Act: -0.1700

Data Index: 2978460 (Open Web Text)

Max Activating Token Index: 478

Text #9

Max Range: 3.5736. Min Range: -3.5736

Max Act: 3.4916. Min Act: -0.1700

Data Index: 6937034 (Open Web Text)

Max Activating Token Index: 1013

Text #10

Max Range: 3.5736. Min Range: -3.5736

Max Act: 3.4617. Min Act: -0.1700

Data Index: 353550 (Open Web Text)

Max Activating Token Index: 419

Text #11

Max Range: 3.5736. Min Range: -3.5736

Max Act: 3.4761. Min Act: -0.1700

Data Index: 3740403 (Open Web Text)

Max Activating Token Index: 183

Text #12

Max Range: 3.5736. Min Range: -3.5736

Max Act: 3.4755. Min Act: -0.1700

Data Index: 3207470 (Open Web Text)

Max Activating Token Index: 36

Text #13

Max Range: 3.5736. Min Range: -3.5736

Max Act: 3.4570. Min Act: -0.1700

Data Index: 5770603 (Open Web Text)

Max Activating Token Index: 226

Text #14

Max Range: 3.5736. Min Range: -3.5736

Max Act: 3.4682. Min Act: -0.1700

Data Index: 7036174 (Open Web Text)

Max Activating Token Index: 219

Text #15

Max Range: 3.5736. Min Range: -3.5736

Max Act: 3.4767. Min Act: -0.1700

Data Index: 7687059 (Open Web Text)

Max Activating Token Index: 669

Text #16

Max Range: 3.5736. Min Range: -3.5736

Max Act: 3.4372. Min Act: -0.1700

Data Index: 6105445 (Open Web Text)

Max Activating Token Index: 48

Text #17

Max Range: 3.5736. Min Range: -3.5736

Max Act: 3.4355. Min Act: -0.1700

Data Index: 4406190 (Open Web Text)

Max Activating Token Index: 187

Text #18

Max Range: 3.5736. Min Range: -3.5736

Max Act: 3.4415. Min Act: -0.1700

Data Index: 501334 (Open Web Text)

Max Activating Token Index: 29

Text #19

Max Range: 3.5736. Min Range: -3.5736

Max Act: 3.4469. Min Act: -0.1700

Data Index: 4893655 (Open Web Text)

Max Activating Token Index: 5