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

Dataset: Open Web Text

Neuron 2375 in Layer 5

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: 4.8298. Min Range: -4.8298

Max Act: 4.7407. Min Act: -0.1700

Data Index: 1523655 (Open Web Text)

Max Activating Token Index: 483

Text #1

Max Range: 4.8298. Min Range: -4.8298

Max Act: 4.8298. Min Act: -0.1700

Data Index: 5810125 (Open Web Text)

Max Activating Token Index: 514

Text #2

Max Range: 4.8298. Min Range: -4.8298

Max Act: 4.7600. Min Act: -0.1700

Data Index: 4890185 (Open Web Text)

Max Activating Token Index: 261

Text #3

Max Range: 4.8298. Min Range: -4.8298

Max Act: 4.6601. Min Act: -0.1700

Data Index: 4039404 (Open Web Text)

Max Activating Token Index: 428

Text #4

Max Range: 4.8298. Min Range: -4.8298

Max Act: 4.7149. Min Act: -0.1700

Data Index: 6441229 (Open Web Text)

Max Activating Token Index: 272

Text #5

Max Range: 4.8298. Min Range: -4.8298

Max Act: 4.6841. Min Act: -0.1700

Data Index: 2251914 (Open Web Text)

Max Activating Token Index: 962

Text #6

Max Range: 4.8298. Min Range: -4.8298

Max Act: 4.6051. Min Act: -0.1700

Data Index: 983937 (Open Web Text)

Max Activating Token Index: 479

Text #7

Max Range: 4.8298. Min Range: -4.8298

Max Act: 4.6104. Min Act: -0.1700

Data Index: 4137103 (Open Web Text)

Max Activating Token Index: 567

Text #8

Max Range: 4.8298. Min Range: -4.8298

Max Act: 4.6229. Min Act: -0.1700

Data Index: 3528918 (Open Web Text)

Max Activating Token Index: 466

Text #9

Max Range: 4.8298. Min Range: -4.8298

Max Act: 4.5949. Min Act: -0.1700

Data Index: 1443765 (Open Web Text)

Max Activating Token Index: 596

Text #10

Max Range: 4.8298. Min Range: -4.8298

Max Act: 4.6339. Min Act: -0.1700

Data Index: 50632 (Open Web Text)

Max Activating Token Index: 604

Text #11

Max Range: 4.8298. Min Range: -4.8298

Max Act: 4.5713. Min Act: -0.1700

Data Index: 3588851 (Open Web Text)

Max Activating Token Index: 484

Text #12

Max Range: 4.8298. Min Range: -4.8298

Max Act: 4.6134. Min Act: -0.1700

Data Index: 3171855 (Open Web Text)

Max Activating Token Index: 588

Text #13

Max Range: 4.8298. Min Range: -4.8298

Max Act: 4.6350. Min Act: -0.1700

Data Index: 2559048 (Open Web Text)

Max Activating Token Index: 529

Text #14

Max Range: 4.8298. Min Range: -4.8298

Max Act: 4.5931. Min Act: -0.1700

Data Index: 1331568 (Open Web Text)

Max Activating Token Index: 461

Text #15

Max Range: 4.8298. Min Range: -4.8298

Max Act: 4.5425. Min Act: -0.1700

Data Index: 4158371 (Open Web Text)

Max Activating Token Index: 987

Text #16

Max Range: 4.8298. Min Range: -4.8298

Max Act: 4.5986. Min Act: -0.1700

Data Index: 4434779 (Open Web Text)

Max Activating Token Index: 352

Text #17

Max Range: 4.8298. Min Range: -4.8298

Max Act: 4.5697. Min Act: -0.1700

Data Index: 3350927 (Open Web Text)

Max Activating Token Index: 582

Text #18

Max Range: 4.8298. Min Range: -4.8298

Max Act: 4.5669. Min Act: -0.1700

Data Index: 3332142 (Open Web Text)

Max Activating Token Index: 71

Text #19

Max Range: 4.8298. Min Range: -4.8298

Max Act: 4.5394. Min Act: -0.1700

Data Index: 1335261 (Open Web Text)

Max Activating Token Index: 914