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

Dataset: Open Web Text

Neuron 3071 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: 3.5291. Min Range: -3.5291

Max Act: 3.5291. Min Act: -0.1700

Data Index: 2210137 (Open Web Text)

Max Activating Token Index: 808

Text #1

Max Range: 3.5291. Min Range: -3.5291

Max Act: 3.3891. Min Act: -0.1700

Data Index: 1133967 (Open Web Text)

Max Activating Token Index: 698

Text #2

Max Range: 3.5291. Min Range: -3.5291

Max Act: 3.3789. Min Act: -0.1700

Data Index: 6114801 (Open Web Text)

Max Activating Token Index: 916

Text #3

Max Range: 3.5291. Min Range: -3.5291

Max Act: 3.3623. Min Act: -0.1700

Data Index: 2950423 (Open Web Text)

Max Activating Token Index: 595

Text #4

Max Range: 3.5291. Min Range: -3.5291

Max Act: 3.3118. Min Act: -0.1700

Data Index: 5879990 (Open Web Text)

Max Activating Token Index: 155

Text #5

Max Range: 3.5291. Min Range: -3.5291

Max Act: 3.2537. Min Act: -0.1700

Data Index: 4927432 (Open Web Text)

Max Activating Token Index: 947

Text #6

Max Range: 3.5291. Min Range: -3.5291

Max Act: 3.2881. Min Act: -0.1700

Data Index: 7952611 (Open Web Text)

Max Activating Token Index: 481

Text #7

Max Range: 3.5291. Min Range: -3.5291

Max Act: 3.2861. Min Act: -0.1700

Data Index: 8824946 (Open Web Text)

Max Activating Token Index: 1019

Text #8

Max Range: 3.5291. Min Range: -3.5291

Max Act: 3.2342. Min Act: -0.1700

Data Index: 4164379 (Open Web Text)

Max Activating Token Index: 164

Text #9

Max Range: 3.5291. Min Range: -3.5291

Max Act: 3.2539. Min Act: -0.1700

Data Index: 4370764 (Open Web Text)

Max Activating Token Index: 122

Text #10

Max Range: 3.5291. Min Range: -3.5291

Max Act: 3.2592. Min Act: -0.1700

Data Index: 3240775 (Open Web Text)

Max Activating Token Index: 756

Text #11

Max Range: 3.5291. Min Range: -3.5291

Max Act: 3.2471. Min Act: -0.1700

Data Index: 1907637 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 3.5291. Min Range: -3.5291

Max Act: 3.2379. Min Act: -0.1700

Data Index: 4933908 (Open Web Text)

Max Activating Token Index: 293

Text #13

Max Range: 3.5291. Min Range: -3.5291

Max Act: 3.2157. Min Act: -0.1700

Data Index: 8562918 (Open Web Text)

Max Activating Token Index: 273

Text #14

Max Range: 3.5291. Min Range: -3.5291

Max Act: 3.2365. Min Act: -0.1700

Data Index: 7677837 (Open Web Text)

Max Activating Token Index: 432

Text #15

Max Range: 3.5291. Min Range: -3.5291

Max Act: 3.2439. Min Act: -0.1700

Data Index: 3899738 (Open Web Text)

Max Activating Token Index: 276

Text #16

Max Range: 3.5291. Min Range: -3.5291

Max Act: 3.2055. Min Act: -0.1700

Data Index: 1290089 (Open Web Text)

Max Activating Token Index: 276

Text #17

Max Range: 3.5291. Min Range: -3.5291

Max Act: 3.2332. Min Act: -0.1700

Data Index: 7225269 (Open Web Text)

Max Activating Token Index: 716

Text #18

Max Range: 3.5291. Min Range: -3.5291

Max Act: 3.1914. Min Act: -0.1700

Data Index: 7065224 (Open Web Text)

Max Activating Token Index: 516

Text #19

Max Range: 3.5291. Min Range: -3.5291

Max Act: 3.2006. Min Act: -0.1700

Data Index: 2512278 (Open Web Text)

Max Activating Token Index: 214