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

Dataset: Open Web Text

Neuron 490 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: 3.3671. Min Range: -3.3671

Max Act: 3.3577. Min Act: -0.1700

Data Index: 4878156 (Open Web Text)

Max Activating Token Index: 359

Text #1

Max Range: 3.3671. Min Range: -3.3671

Max Act: 3.3671. Min Act: -0.1700

Data Index: 130723 (Open Web Text)

Max Activating Token Index: 10

Text #2

Max Range: 3.3671. Min Range: -3.3671

Max Act: 3.2002. Min Act: -0.1700

Data Index: 8090973 (Open Web Text)

Max Activating Token Index: 421

Text #3

Max Range: 3.3671. Min Range: -3.3671

Max Act: 3.1596. Min Act: -0.1700

Data Index: 4977754 (Open Web Text)

Max Activating Token Index: 114

Text #4

Max Range: 3.3671. Min Range: -3.3671

Max Act: 3.2095. Min Act: -0.1700

Data Index: 1991433 (Open Web Text)

Max Activating Token Index: 250

Text #5

Max Range: 3.3671. Min Range: -3.3671

Max Act: 3.2088. Min Act: -0.1700

Data Index: 1014248 (Open Web Text)

Max Activating Token Index: 732

Text #6

Max Range: 3.3671. Min Range: -3.3671

Max Act: 3.1405. Min Act: -0.1700

Data Index: 2517594 (Open Web Text)

Max Activating Token Index: 286

Text #7

Max Range: 3.3671. Min Range: -3.3671

Max Act: 3.0954. Min Act: -0.1700

Data Index: 4594776 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.3671. Min Range: -3.3671

Max Act: 3.0994. Min Act: -0.1700

Data Index: 721126 (Open Web Text)

Max Activating Token Index: 559

Text #9

Max Range: 3.3671. Min Range: -3.3671

Max Act: 3.0813. Min Act: -0.1700

Data Index: 7865521 (Open Web Text)

Max Activating Token Index: 422

Text #10

Max Range: 3.3671. Min Range: -3.3671

Max Act: 3.0480. Min Act: -0.1700

Data Index: 7834991 (Open Web Text)

Max Activating Token Index: 497

Text #11

Max Range: 3.3671. Min Range: -3.3671

Max Act: 3.0567. Min Act: -0.1700

Data Index: 935375 (Open Web Text)

Max Activating Token Index: 77

Text #12

Max Range: 3.3671. Min Range: -3.3671

Max Act: 3.0686. Min Act: -0.1700

Data Index: 2042607 (Open Web Text)

Max Activating Token Index: 87

Text #13

Max Range: 3.3671. Min Range: -3.3671

Max Act: 3.0536. Min Act: -0.1700

Data Index: 8273680 (Open Web Text)

Max Activating Token Index: 373

Text #14

Max Range: 3.3671. Min Range: -3.3671

Max Act: 3.0324. Min Act: -0.1700

Data Index: 101304 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.3671. Min Range: -3.3671

Max Act: 3.0010. Min Act: -0.1700

Data Index: 6327009 (Open Web Text)

Max Activating Token Index: 384

Text #16

Max Range: 3.3671. Min Range: -3.3671

Max Act: 3.0377. Min Act: -0.1700

Data Index: 6247224 (Open Web Text)

Max Activating Token Index: 966

Text #17

Max Range: 3.3671. Min Range: -3.3671

Max Act: 3.0047. Min Act: -0.1700

Data Index: 6048090 (Open Web Text)

Max Activating Token Index: 558

Text #18

Max Range: 3.3671. Min Range: -3.3671

Max Act: 3.0556. Min Act: -0.1700

Data Index: 5623071 (Open Web Text)

Max Activating Token Index: 804

Text #19

Max Range: 3.3671. Min Range: -3.3671

Max Act: 3.0089. Min Act: -0.1700

Data Index: 7949914 (Open Web Text)

Max Activating Token Index: 537