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

Dataset: Open Web Text

Neuron 1015 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: 4.4558. Min Range: -4.4558

Max Act: 4.4558. Min Act: -0.1700

Data Index: 3336793 (Open Web Text)

Max Activating Token Index: 348

Text #1

Max Range: 4.4558. Min Range: -4.4558

Max Act: 4.4047. Min Act: -0.1700

Data Index: 1330235 (Open Web Text)

Max Activating Token Index: 534

Text #2

Max Range: 4.4558. Min Range: -4.4558

Max Act: 4.3200. Min Act: -0.1700

Data Index: 2246133 (Open Web Text)

Max Activating Token Index: 417

Text #3

Max Range: 4.4558. Min Range: -4.4558

Max Act: 4.3253. Min Act: -0.1700

Data Index: 7279323 (Open Web Text)

Max Activating Token Index: 960

Text #4

Max Range: 4.4558. Min Range: -4.4558

Max Act: 4.3090. Min Act: -0.1700

Data Index: 8067236 (Open Web Text)

Max Activating Token Index: 100

Text #5

Max Range: 4.4558. Min Range: -4.4558

Max Act: 4.2962. Min Act: -0.1700

Data Index: 8456981 (Open Web Text)

Max Activating Token Index: 74

Text #6

Max Range: 4.4558. Min Range: -4.4558

Max Act: 4.2509. Min Act: -0.1700

Data Index: 6878343 (Open Web Text)

Max Activating Token Index: 32

Text #7

Max Range: 4.4558. Min Range: -4.4558

Max Act: 4.2835. Min Act: -0.1700

Data Index: 8761683 (Open Web Text)

Max Activating Token Index: 499

Text #8

Max Range: 4.4558. Min Range: -4.4558

Max Act: 4.2304. Min Act: -0.1700

Data Index: 4300852 (Open Web Text)

Max Activating Token Index: 231

Text #9

Max Range: 4.4558. Min Range: -4.4558

Max Act: 4.1998. Min Act: -0.1700

Data Index: 540387 (Open Web Text)

Max Activating Token Index: 98

Text #10

Max Range: 4.4558. Min Range: -4.4558

Max Act: 4.1330. Min Act: -0.1700

Data Index: 53100 (Open Web Text)

Max Activating Token Index: 654

Text #11

Max Range: 4.4558. Min Range: -4.4558

Max Act: 4.1763. Min Act: -0.1700

Data Index: 6808013 (Open Web Text)

Max Activating Token Index: 748

Text #12

Max Range: 4.4558. Min Range: -4.4558

Max Act: 4.1643. Min Act: -0.1700

Data Index: 8525767 (Open Web Text)

Max Activating Token Index: 270

Text #13

Max Range: 4.4558. Min Range: -4.4558

Max Act: 4.1270. Min Act: -0.1700

Data Index: 2083067 (Open Web Text)

Max Activating Token Index: 433

Text #14

Max Range: 4.4558. Min Range: -4.4558

Max Act: 4.1508. Min Act: -0.1700

Data Index: 6555389 (Open Web Text)

Max Activating Token Index: 181

Text #15

Max Range: 4.4558. Min Range: -4.4558

Max Act: 4.1526. Min Act: -0.1700

Data Index: 3776996 (Open Web Text)

Max Activating Token Index: 262

Text #16

Max Range: 4.4558. Min Range: -4.4558

Max Act: 4.1425. Min Act: -0.1700

Data Index: 4948723 (Open Web Text)

Max Activating Token Index: 343

Text #17

Max Range: 4.4558. Min Range: -4.4558

Max Act: 4.0819. Min Act: -0.1700

Data Index: 4424273 (Open Web Text)

Max Activating Token Index: 514

Text #18

Max Range: 4.4558. Min Range: -4.4558

Max Act: 4.1089. Min Act: -0.1700

Data Index: 1417149 (Open Web Text)

Max Activating Token Index: 473

Text #19

Max Range: 4.4558. Min Range: -4.4558

Max Act: 4.1031. Min Act: -0.1700

Data Index: 3111858 (Open Web Text)

Max Activating Token Index: 933