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

Dataset: Open Web Text

Neuron 1640 in Layer 6

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: 3.0229. Min Range: -3.0229

Max Act: 3.0229. Min Act: -0.1700

Data Index: 7506620 (Open Web Text)

Max Activating Token Index: 218

Text #1

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.9327. Min Act: -0.1700

Data Index: 2825343 (Open Web Text)

Max Activating Token Index: 300

Text #2

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.8183. Min Act: -0.1700

Data Index: 472242 (Open Web Text)

Max Activating Token Index: 567

Text #3

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.8006. Min Act: -0.1700

Data Index: 7445652 (Open Web Text)

Max Activating Token Index: 51

Text #4

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.7854. Min Act: -0.1700

Data Index: 717711 (Open Web Text)

Max Activating Token Index: 482

Text #5

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.8192. Min Act: -0.1700

Data Index: 5314082 (Open Web Text)

Max Activating Token Index: 25

Text #6

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.7892. Min Act: -0.1700

Data Index: 2944372 (Open Web Text)

Max Activating Token Index: 250

Text #7

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.7584. Min Act: -0.1700

Data Index: 4602866 (Open Web Text)

Max Activating Token Index: 599

Text #8

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.7690. Min Act: -0.1700

Data Index: 185277 (Open Web Text)

Max Activating Token Index: 328

Text #9

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.7467. Min Act: -0.1700

Data Index: 4619988 (Open Web Text)

Max Activating Token Index: 617

Text #10

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.7596. Min Act: -0.1700

Data Index: 1510067 (Open Web Text)

Max Activating Token Index: 673

Text #11

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.7572. Min Act: -0.1700

Data Index: 8470333 (Open Web Text)

Max Activating Token Index: 359

Text #12

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.7698. Min Act: -0.1700

Data Index: 8294969 (Open Web Text)

Max Activating Token Index: 611

Text #13

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.7654. Min Act: -0.1700

Data Index: 7957605 (Open Web Text)

Max Activating Token Index: 23

Text #14

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.7542. Min Act: -0.1700

Data Index: 7046855 (Open Web Text)

Max Activating Token Index: 755

Text #15

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.7580. Min Act: -0.1700

Data Index: 5952565 (Open Web Text)

Max Activating Token Index: 158

Text #16

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.7645. Min Act: -0.1700

Data Index: 3420885 (Open Web Text)

Max Activating Token Index: 592

Text #17

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.7406. Min Act: -0.1700

Data Index: 2854151 (Open Web Text)

Max Activating Token Index: 267

Text #18

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.7326. Min Act: -0.1700

Data Index: 658514 (Open Web Text)

Max Activating Token Index: 634

Text #19

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.7482. Min Act: -0.1700

Data Index: 1546833 (Open Web Text)

Max Activating Token Index: 147