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

Dataset: Open Web Text

Neuron 2735 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: 4.4871. Min Range: -4.4871

Max Act: 4.4871. Min Act: -0.1700

Data Index: 8673373 (Open Web Text)

Max Activating Token Index: 805

Text #1

Max Range: 4.4871. Min Range: -4.4871

Max Act: 4.4435. Min Act: -0.1700

Data Index: 1748640 (Open Web Text)

Max Activating Token Index: 16

Text #2

Max Range: 4.4871. Min Range: -4.4871

Max Act: 4.4413. Min Act: -0.1700

Data Index: 8520943 (Open Web Text)

Max Activating Token Index: 929

Text #3

Max Range: 4.4871. Min Range: -4.4871

Max Act: 4.3944. Min Act: -0.1700

Data Index: 2312153 (Open Web Text)

Max Activating Token Index: 745

Text #4

Max Range: 4.4871. Min Range: -4.4871

Max Act: 4.4137. Min Act: -0.1700

Data Index: 5644176 (Open Web Text)

Max Activating Token Index: 243

Text #5

Max Range: 4.4871. Min Range: -4.4871

Max Act: 4.4277. Min Act: -0.1700

Data Index: 5712627 (Open Web Text)

Max Activating Token Index: 237

Text #6

Max Range: 4.4871. Min Range: -4.4871

Max Act: 4.4250. Min Act: -0.1700

Data Index: 5822132 (Open Web Text)

Max Activating Token Index: 217

Text #7

Max Range: 4.4871. Min Range: -4.4871

Max Act: 4.4190. Min Act: -0.1700

Data Index: 4858878 (Open Web Text)

Max Activating Token Index: 924

Text #8

Max Range: 4.4871. Min Range: -4.4871

Max Act: 4.3709. Min Act: -0.1700

Data Index: 4228263 (Open Web Text)

Max Activating Token Index: 592

Text #9

Max Range: 4.4871. Min Range: -4.4871

Max Act: 4.3549. Min Act: -0.1700

Data Index: 7050589 (Open Web Text)

Max Activating Token Index: 703

Text #10

Max Range: 4.4871. Min Range: -4.4871

Max Act: 4.3796. Min Act: -0.1700

Data Index: 2194999 (Open Web Text)

Max Activating Token Index: 247

Text #11

Max Range: 4.4871. Min Range: -4.4871

Max Act: 4.3334. Min Act: -0.1700

Data Index: 6718807 (Open Web Text)

Max Activating Token Index: 971

Text #12

Max Range: 4.4871. Min Range: -4.4871

Max Act: 4.3556. Min Act: -0.1700

Data Index: 7274665 (Open Web Text)

Max Activating Token Index: 259

Text #13

Max Range: 4.4871. Min Range: -4.4871

Max Act: 4.3378. Min Act: -0.1700

Data Index: 4662253 (Open Web Text)

Max Activating Token Index: 187

Text #14

Max Range: 4.4871. Min Range: -4.4871

Max Act: 4.3375. Min Act: -0.1700

Data Index: 3684571 (Open Web Text)

Max Activating Token Index: 202

Text #15

Max Range: 4.4871. Min Range: -4.4871

Max Act: 4.3132. Min Act: -0.1700

Data Index: 3007836 (Open Web Text)

Max Activating Token Index: 878

Text #16

Max Range: 4.4871. Min Range: -4.4871

Max Act: 4.3069. Min Act: -0.1700

Data Index: 6935981 (Open Web Text)

Max Activating Token Index: 180

Text #17

Max Range: 4.4871. Min Range: -4.4871

Max Act: 4.3245. Min Act: -0.1700

Data Index: 3553901 (Open Web Text)

Max Activating Token Index: 91

Text #18

Max Range: 4.4871. Min Range: -4.4871

Max Act: 4.3297. Min Act: -0.1700

Data Index: 730423 (Open Web Text)

Max Activating Token Index: 900

Text #19

Max Range: 4.4871. Min Range: -4.4871

Max Act: 4.3082. Min Act: -0.1700

Data Index: 2438241 (Open Web Text)

Max Activating Token Index: 823