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

Dataset: Open Web Text

Neuron 2258 in Layer 2

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: 3.4397. Min Range: -3.4397

Max Act: 3.4397. Min Act: -0.1700

Data Index: 5115310 (Open Web Text)

Max Activating Token Index: 71

Text #1

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.4104. Min Act: -0.1700

Data Index: 221840 (Open Web Text)

Max Activating Token Index: 44

Text #2

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.3636. Min Act: -0.1700

Data Index: 8699037 (Open Web Text)

Max Activating Token Index: 806

Text #3

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.3635. Min Act: -0.1700

Data Index: 3301228 (Open Web Text)

Max Activating Token Index: 312

Text #4

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.3375. Min Act: -0.1700

Data Index: 5329904 (Open Web Text)

Max Activating Token Index: 180

Text #5

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.3427. Min Act: -0.1700

Data Index: 2539141 (Open Web Text)

Max Activating Token Index: 60

Text #6

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.3201. Min Act: -0.1700

Data Index: 8704537 (Open Web Text)

Max Activating Token Index: 566

Text #7

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.3151. Min Act: -0.1700

Data Index: 1873229 (Open Web Text)

Max Activating Token Index: 942

Text #8

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.3137. Min Act: -0.1700

Data Index: 2920095 (Open Web Text)

Max Activating Token Index: 985

Text #9

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.2879. Min Act: -0.1700

Data Index: 1967101 (Open Web Text)

Max Activating Token Index: 507

Text #10

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.3016. Min Act: -0.1700

Data Index: 2754972 (Open Web Text)

Max Activating Token Index: 402

Text #11

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.2743. Min Act: -0.1700

Data Index: 125523 (Open Web Text)

Max Activating Token Index: 866

Text #12

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.2908. Min Act: -0.1700

Data Index: 8776560 (Open Web Text)

Max Activating Token Index: 123

Text #13

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.2685. Min Act: -0.1700

Data Index: 8287652 (Open Web Text)

Max Activating Token Index: 67

Text #14

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.2797. Min Act: -0.1700

Data Index: 4340309 (Open Web Text)

Max Activating Token Index: 827

Text #15

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.2810. Min Act: -0.1700

Data Index: 8799273 (Open Web Text)

Max Activating Token Index: 666

Text #16

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.2630. Min Act: -0.1700

Data Index: 1078487 (Open Web Text)

Max Activating Token Index: 945

Text #17

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.2733. Min Act: -0.1700

Data Index: 7612309 (Open Web Text)

Max Activating Token Index: 668

Text #18

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.2612. Min Act: -0.1700

Data Index: 8308874 (Open Web Text)

Max Activating Token Index: 928

Text #19

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.2555. Min Act: -0.1700

Data Index: 6720901 (Open Web Text)

Max Activating Token Index: 358