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

Dataset: Open Web Text

Neuron 2119 in Layer 3

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: 4.5527. Min Range: -4.5527

Max Act: 4.5527. Min Act: -0.1700

Data Index: 4520146 (Open Web Text)

Max Activating Token Index: 74

Text #1

Max Range: 4.5527. Min Range: -4.5527

Max Act: 4.4284. Min Act: -0.1700

Data Index: 2613921 (Open Web Text)

Max Activating Token Index: 191

Text #2

Max Range: 4.5527. Min Range: -4.5527

Max Act: 4.4293. Min Act: -0.1700

Data Index: 2550991 (Open Web Text)

Max Activating Token Index: 50

Text #3

Max Range: 4.5527. Min Range: -4.5527

Max Act: 4.4096. Min Act: -0.1700

Data Index: 661438 (Open Web Text)

Max Activating Token Index: 289

Text #4

Max Range: 4.5527. Min Range: -4.5527

Max Act: 4.4140. Min Act: -0.1700

Data Index: 4954849 (Open Web Text)

Max Activating Token Index: 528

Text #5

Max Range: 4.5527. Min Range: -4.5527

Max Act: 4.4104. Min Act: -0.1700

Data Index: 4957062 (Open Web Text)

Max Activating Token Index: 959

Text #6

Max Range: 4.5527. Min Range: -4.5527

Max Act: 4.4012. Min Act: -0.1700

Data Index: 1320833 (Open Web Text)

Max Activating Token Index: 996

Text #7

Max Range: 4.5527. Min Range: -4.5527

Max Act: 4.4078. Min Act: -0.1700

Data Index: 4011848 (Open Web Text)

Max Activating Token Index: 263

Text #8

Max Range: 4.5527. Min Range: -4.5527

Max Act: 4.3841. Min Act: -0.1700

Data Index: 8340824 (Open Web Text)

Max Activating Token Index: 74

Text #9

Max Range: 4.5527. Min Range: -4.5527

Max Act: 4.3910. Min Act: -0.1700

Data Index: 6986440 (Open Web Text)

Max Activating Token Index: 906

Text #10

Max Range: 4.5527. Min Range: -4.5527

Max Act: 4.3750. Min Act: -0.1700

Data Index: 2071038 (Open Web Text)

Max Activating Token Index: 92

Text #11

Max Range: 4.5527. Min Range: -4.5527

Max Act: 4.3389. Min Act: -0.1700

Data Index: 6383244 (Open Web Text)

Max Activating Token Index: 96

Text #12

Max Range: 4.5527. Min Range: -4.5527

Max Act: 4.3594. Min Act: -0.1700

Data Index: 6746452 (Open Web Text)

Max Activating Token Index: 182

Text #13

Max Range: 4.5527. Min Range: -4.5527

Max Act: 4.3408. Min Act: -0.1700

Data Index: 6814435 (Open Web Text)

Max Activating Token Index: 70

Text #14

Max Range: 4.5527. Min Range: -4.5527

Max Act: 4.3683. Min Act: -0.1700

Data Index: 3561614 (Open Web Text)

Max Activating Token Index: 558

Text #15

Max Range: 4.5527. Min Range: -4.5527

Max Act: 4.3622. Min Act: -0.1700

Data Index: 3064139 (Open Web Text)

Max Activating Token Index: 897

Text #16

Max Range: 4.5527. Min Range: -4.5527

Max Act: 4.3299. Min Act: -0.1700

Data Index: 7335275 (Open Web Text)

Max Activating Token Index: 492

Text #17

Max Range: 4.5527. Min Range: -4.5527

Max Act: 4.3514. Min Act: -0.1700

Data Index: 1037616 (Open Web Text)

Max Activating Token Index: 68

Text #18

Max Range: 4.5527. Min Range: -4.5527

Max Act: 4.3557. Min Act: -0.1700

Data Index: 7765346 (Open Web Text)

Max Activating Token Index: 117

Text #19

Max Range: 4.5527. Min Range: -4.5527

Max Act: 4.3263. Min Act: -0.1700

Data Index: 7840049 (Open Web Text)

Max Activating Token Index: 142