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

Dataset: Open Web Text

Neuron 416 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: 3.9771. Min Range: -3.9771

Max Act: 3.9771. Min Act: -0.1700

Data Index: 724430 (Open Web Text)

Max Activating Token Index: 511

Text #1

Max Range: 3.9771. Min Range: -3.9771

Max Act: 3.8906. Min Act: -0.1700

Data Index: 6038512 (Open Web Text)

Max Activating Token Index: 514

Text #2

Max Range: 3.9771. Min Range: -3.9771

Max Act: 3.8544. Min Act: -0.1700

Data Index: 6279516 (Open Web Text)

Max Activating Token Index: 343

Text #3

Max Range: 3.9771. Min Range: -3.9771

Max Act: 3.7729. Min Act: -0.1700

Data Index: 8400567 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 3.9771. Min Range: -3.9771

Max Act: 3.7215. Min Act: -0.1700

Data Index: 4193794 (Open Web Text)

Max Activating Token Index: 541

Text #5

Max Range: 3.9771. Min Range: -3.9771

Max Act: 3.7287. Min Act: -0.1700

Data Index: 439354 (Open Web Text)

Max Activating Token Index: 634

Text #6

Max Range: 3.9771. Min Range: -3.9771

Max Act: 3.7341. Min Act: -0.1700

Data Index: 8517143 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 3.9771. Min Range: -3.9771

Max Act: 3.6771. Min Act: -0.1700

Data Index: 4132724 (Open Web Text)

Max Activating Token Index: 345

Text #8

Max Range: 3.9771. Min Range: -3.9771

Max Act: 3.7123. Min Act: -0.1700

Data Index: 540638 (Open Web Text)

Max Activating Token Index: 487

Text #9

Max Range: 3.9771. Min Range: -3.9771

Max Act: 3.7180. Min Act: -0.1700

Data Index: 2815426 (Open Web Text)

Max Activating Token Index: 13

Text #10

Max Range: 3.9771. Min Range: -3.9771

Max Act: 3.6901. Min Act: -0.1700

Data Index: 6409705 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.9771. Min Range: -3.9771

Max Act: 3.7192. Min Act: -0.1700

Data Index: 461171 (Open Web Text)

Max Activating Token Index: 272

Text #12

Max Range: 3.9771. Min Range: -3.9771

Max Act: 3.7032. Min Act: -0.1700

Data Index: 1348279 (Open Web Text)

Max Activating Token Index: 146

Text #13

Max Range: 3.9771. Min Range: -3.9771

Max Act: 3.6305. Min Act: -0.1700

Data Index: 3931407 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 3.9771. Min Range: -3.9771

Max Act: 3.6567. Min Act: -0.1700

Data Index: 728968 (Open Web Text)

Max Activating Token Index: 954

Text #15

Max Range: 3.9771. Min Range: -3.9771

Max Act: 3.6311. Min Act: -0.1700

Data Index: 2020185 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 3.9771. Min Range: -3.9771

Max Act: 3.6334. Min Act: -0.1700

Data Index: 3442346 (Open Web Text)

Max Activating Token Index: 542

Text #17

Max Range: 3.9771. Min Range: -3.9771

Max Act: 3.6242. Min Act: -0.1700

Data Index: 5403046 (Open Web Text)

Max Activating Token Index: 322

Text #18

Max Range: 3.9771. Min Range: -3.9771

Max Act: 3.6709. Min Act: -0.1700

Data Index: 3258945 (Open Web Text)

Max Activating Token Index: 86

Text #19

Max Range: 3.9771. Min Range: -3.9771

Max Act: 3.6385. Min Act: -0.1700

Data Index: 2123041 (Open Web Text)

Max Activating Token Index: 13