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

Dataset: Open Web Text

Neuron 161 in Layer 4

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: 3.9952. Min Range: -3.9952

Max Act: 3.9952. Min Act: -0.1700

Data Index: 2948917 (Open Web Text)

Max Activating Token Index: 254

Text #1

Max Range: 3.9952. Min Range: -3.9952

Max Act: 3.9017. Min Act: -0.1700

Data Index: 5994882 (Open Web Text)

Max Activating Token Index: 633

Text #2

Max Range: 3.9952. Min Range: -3.9952

Max Act: 3.7214. Min Act: -0.1700

Data Index: 1688321 (Open Web Text)

Max Activating Token Index: 292

Text #3

Max Range: 3.9952. Min Range: -3.9952

Max Act: 3.6555. Min Act: -0.1700

Data Index: 6058871 (Open Web Text)

Max Activating Token Index: 40

Text #4

Max Range: 3.9952. Min Range: -3.9952

Max Act: 3.4992. Min Act: -0.1700

Data Index: 6233135 (Open Web Text)

Max Activating Token Index: 599

Text #5

Max Range: 3.9952. Min Range: -3.9952

Max Act: 3.4908. Min Act: -0.1700

Data Index: 3667386 (Open Web Text)

Max Activating Token Index: 417

Text #6

Max Range: 3.9952. Min Range: -3.9952

Max Act: 3.4649. Min Act: -0.1700

Data Index: 1734792 (Open Web Text)

Max Activating Token Index: 92

Text #7

Max Range: 3.9952. Min Range: -3.9952

Max Act: 3.4044. Min Act: -0.1700

Data Index: 7924489 (Open Web Text)

Max Activating Token Index: 351

Text #8

Max Range: 3.9952. Min Range: -3.9952

Max Act: 3.3111. Min Act: -0.1700

Data Index: 1460467 (Open Web Text)

Max Activating Token Index: 704

Text #9

Max Range: 3.9952. Min Range: -3.9952

Max Act: 3.2856. Min Act: -0.1700

Data Index: 4052709 (Open Web Text)

Max Activating Token Index: 374

Text #10

Max Range: 3.9952. Min Range: -3.9952

Max Act: 3.2943. Min Act: -0.1700

Data Index: 151537 (Open Web Text)

Max Activating Token Index: 865

Text #11

Max Range: 3.9952. Min Range: -3.9952

Max Act: 3.2872. Min Act: -0.1700

Data Index: 2129887 (Open Web Text)

Max Activating Token Index: 731

Text #12

Max Range: 3.9952. Min Range: -3.9952

Max Act: 3.2710. Min Act: -0.1700

Data Index: 5253349 (Open Web Text)

Max Activating Token Index: 198

Text #13

Max Range: 3.9952. Min Range: -3.9952

Max Act: 3.2905. Min Act: -0.1700

Data Index: 1388210 (Open Web Text)

Max Activating Token Index: 331

Text #14

Max Range: 3.9952. Min Range: -3.9952

Max Act: 3.2662. Min Act: -0.1700

Data Index: 4270329 (Open Web Text)

Max Activating Token Index: 265

Text #15

Max Range: 3.9952. Min Range: -3.9952

Max Act: 3.2936. Min Act: -0.1700

Data Index: 4449384 (Open Web Text)

Max Activating Token Index: 889

Text #16

Max Range: 3.9952. Min Range: -3.9952

Max Act: 3.2522. Min Act: -0.1700

Data Index: 236559 (Open Web Text)

Max Activating Token Index: 607

Text #17

Max Range: 3.9952. Min Range: -3.9952

Max Act: 3.2705. Min Act: -0.1700

Data Index: 7617486 (Open Web Text)

Max Activating Token Index: 199

Text #18

Max Range: 3.9952. Min Range: -3.9952

Max Act: 3.2474. Min Act: -0.1700

Data Index: 1250562 (Open Web Text)

Max Activating Token Index: 185

Text #19

Max Range: 3.9952. Min Range: -3.9952

Max Act: 3.2443. Min Act: -0.1700

Data Index: 3332545 (Open Web Text)

Max Activating Token Index: 732