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

Dataset: Open Web Text

Neuron 2455 in Layer 3

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: 4.5773. Min Range: -4.5773

Max Act: 4.5773. Min Act: -0.1700

Data Index: 3281550 (Open Web Text)

Max Activating Token Index: 435

Text #1

Max Range: 4.5773. Min Range: -4.5773

Max Act: 4.4778. Min Act: -0.1700

Data Index: 8671814 (Open Web Text)

Max Activating Token Index: 101

Text #2

Max Range: 4.5773. Min Range: -4.5773

Max Act: 4.4533. Min Act: -0.1700

Data Index: 6197844 (Open Web Text)

Max Activating Token Index: 548

Text #3

Max Range: 4.5773. Min Range: -4.5773

Max Act: 4.4427. Min Act: -0.1700

Data Index: 3280501 (Open Web Text)

Max Activating Token Index: 82

Text #4

Max Range: 4.5773. Min Range: -4.5773

Max Act: 4.4603. Min Act: -0.1700

Data Index: 1609825 (Open Web Text)

Max Activating Token Index: 312

Text #5

Max Range: 4.5773. Min Range: -4.5773

Max Act: 4.4147. Min Act: -0.1700

Data Index: 4040571 (Open Web Text)

Max Activating Token Index: 382

Text #6

Max Range: 4.5773. Min Range: -4.5773

Max Act: 4.4471. Min Act: -0.1700

Data Index: 7311832 (Open Web Text)

Max Activating Token Index: 338

Text #7

Max Range: 4.5773. Min Range: -4.5773

Max Act: 4.4266. Min Act: -0.1700

Data Index: 6571556 (Open Web Text)

Max Activating Token Index: 617

Text #8

Max Range: 4.5773. Min Range: -4.5773

Max Act: 4.3846. Min Act: -0.1700

Data Index: 4861329 (Open Web Text)

Max Activating Token Index: 75

Text #9

Max Range: 4.5773. Min Range: -4.5773

Max Act: 4.3255. Min Act: -0.1700

Data Index: 8271624 (Open Web Text)

Max Activating Token Index: 203

Text #10

Max Range: 4.5773. Min Range: -4.5773

Max Act: 4.3523. Min Act: -0.1700

Data Index: 8771686 (Open Web Text)

Max Activating Token Index: 844

Text #11

Max Range: 4.5773. Min Range: -4.5773

Max Act: 4.3311. Min Act: -0.1700

Data Index: 6212883 (Open Web Text)

Max Activating Token Index: 179

Text #12

Max Range: 4.5773. Min Range: -4.5773

Max Act: 4.3141. Min Act: -0.1700

Data Index: 3394520 (Open Web Text)

Max Activating Token Index: 194

Text #13

Max Range: 4.5773. Min Range: -4.5773

Max Act: 4.3338. Min Act: -0.1700

Data Index: 2471381 (Open Web Text)

Max Activating Token Index: 191

Text #14

Max Range: 4.5773. Min Range: -4.5773

Max Act: 4.3340. Min Act: -0.1700

Data Index: 6191955 (Open Web Text)

Max Activating Token Index: 532

Text #15

Max Range: 4.5773. Min Range: -4.5773

Max Act: 4.3238. Min Act: -0.1700

Data Index: 3942394 (Open Web Text)

Max Activating Token Index: 388

Text #16

Max Range: 4.5773. Min Range: -4.5773

Max Act: 4.2785. Min Act: -0.1700

Data Index: 7947914 (Open Web Text)

Max Activating Token Index: 403

Text #17

Max Range: 4.5773. Min Range: -4.5773

Max Act: 4.2927. Min Act: -0.1700

Data Index: 3838736 (Open Web Text)

Max Activating Token Index: 703

Text #18

Max Range: 4.5773. Min Range: -4.5773

Max Act: 4.3027. Min Act: -0.1700

Data Index: 3280500 (Open Web Text)

Max Activating Token Index: 805

Text #19

Max Range: 4.5773. Min Range: -4.5773

Max Act: 4.2840. Min Act: -0.1700

Data Index: 6077679 (Open Web Text)

Max Activating Token Index: 1020