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

Dataset: Open Web Text

Neuron 511 in Layer 6

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: 4.5445. Min Range: -4.5445

Max Act: 4.5102. Min Act: -0.1700

Data Index: 8298877 (Open Web Text)

Max Activating Token Index: 294

Text #1

Max Range: 4.5445. Min Range: -4.5445

Max Act: 4.5445. Min Act: -0.1700

Data Index: 4534837 (Open Web Text)

Max Activating Token Index: 19

Text #2

Max Range: 4.5445. Min Range: -4.5445

Max Act: 4.4721. Min Act: -0.1700

Data Index: 151787 (Open Web Text)

Max Activating Token Index: 282

Text #3

Max Range: 4.5445. Min Range: -4.5445

Max Act: 4.4091. Min Act: -0.1700

Data Index: 6122176 (Open Web Text)

Max Activating Token Index: 61

Text #4

Max Range: 4.5445. Min Range: -4.5445

Max Act: 4.3867. Min Act: -0.1700

Data Index: 7620136 (Open Web Text)

Max Activating Token Index: 847

Text #5

Max Range: 4.5445. Min Range: -4.5445

Max Act: 4.3671. Min Act: -0.1700

Data Index: 6704629 (Open Web Text)

Max Activating Token Index: 841

Text #6

Max Range: 4.5445. Min Range: -4.5445

Max Act: 4.3665. Min Act: -0.1700

Data Index: 4524824 (Open Web Text)

Max Activating Token Index: 189

Text #7

Max Range: 4.5445. Min Range: -4.5445

Max Act: 4.2903. Min Act: -0.1700

Data Index: 212396 (Open Web Text)

Max Activating Token Index: 764

Text #8

Max Range: 4.5445. Min Range: -4.5445

Max Act: 4.3016. Min Act: -0.1700

Data Index: 3452924 (Open Web Text)

Max Activating Token Index: 917

Text #9

Max Range: 4.5445. Min Range: -4.5445

Max Act: 4.2676. Min Act: -0.1700

Data Index: 2842115 (Open Web Text)

Max Activating Token Index: 384

Text #10

Max Range: 4.5445. Min Range: -4.5445

Max Act: 4.2622. Min Act: -0.1700

Data Index: 8271149 (Open Web Text)

Max Activating Token Index: 280

Text #11

Max Range: 4.5445. Min Range: -4.5445

Max Act: 4.2722. Min Act: -0.1700

Data Index: 1006492 (Open Web Text)

Max Activating Token Index: 265

Text #12

Max Range: 4.5445. Min Range: -4.5445

Max Act: 4.2716. Min Act: -0.1700

Data Index: 5595745 (Open Web Text)

Max Activating Token Index: 712

Text #13

Max Range: 4.5445. Min Range: -4.5445

Max Act: 4.2630. Min Act: -0.1700

Data Index: 4534836 (Open Web Text)

Max Activating Token Index: 191

Text #14

Max Range: 4.5445. Min Range: -4.5445

Max Act: 4.2428. Min Act: -0.1700

Data Index: 6384952 (Open Web Text)

Max Activating Token Index: 254

Text #15

Max Range: 4.5445. Min Range: -4.5445

Max Act: 4.2469. Min Act: -0.1700

Data Index: 6001831 (Open Web Text)

Max Activating Token Index: 842

Text #16

Max Range: 4.5445. Min Range: -4.5445

Max Act: 4.2430. Min Act: -0.1700

Data Index: 5341535 (Open Web Text)

Max Activating Token Index: 120

Text #17

Max Range: 4.5445. Min Range: -4.5445

Max Act: 4.2380. Min Act: -0.1700

Data Index: 2775690 (Open Web Text)

Max Activating Token Index: 513

Text #18

Max Range: 4.5445. Min Range: -4.5445

Max Act: 4.2099. Min Act: -0.1700

Data Index: 3565884 (Open Web Text)

Max Activating Token Index: 233

Text #19

Max Range: 4.5445. Min Range: -4.5445

Max Act: 4.2183. Min Act: -0.1700

Data Index: 7719518 (Open Web Text)

Max Activating Token Index: 892