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

Dataset: Open Web Text

Neuron 2180 in Layer 6

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: 6.4396. Min Range: -6.4396

Max Act: 6.4396. Min Act: -0.1700

Data Index: 1746081 (Open Web Text)

Max Activating Token Index: 534

Text #1

Max Range: 6.4396. Min Range: -6.4396

Max Act: 6.3304. Min Act: -0.1700

Data Index: 3771125 (Open Web Text)

Max Activating Token Index: 794

Text #2

Max Range: 6.4396. Min Range: -6.4396

Max Act: 6.1553. Min Act: -0.1700

Data Index: 7466315 (Open Web Text)

Max Activating Token Index: 579

Text #3

Max Range: 6.4396. Min Range: -6.4396

Max Act: 6.1270. Min Act: -0.1700

Data Index: 5189552 (Open Web Text)

Max Activating Token Index: 344

Text #4

Max Range: 6.4396. Min Range: -6.4396

Max Act: 6.1319. Min Act: -0.1700

Data Index: 8353844 (Open Web Text)

Max Activating Token Index: 175

Text #5

Max Range: 6.4396. Min Range: -6.4396

Max Act: 6.1246. Min Act: -0.1700

Data Index: 4775192 (Open Web Text)

Max Activating Token Index: 999

Text #6

Max Range: 6.4396. Min Range: -6.4396

Max Act: 6.0315. Min Act: -0.1700

Data Index: 4242300 (Open Web Text)

Max Activating Token Index: 785

Text #7

Max Range: 6.4396. Min Range: -6.4396

Max Act: 6.0673. Min Act: -0.1700

Data Index: 1861828 (Open Web Text)

Max Activating Token Index: 46

Text #8

Max Range: 6.4396. Min Range: -6.4396

Max Act: 6.0214. Min Act: -0.1700

Data Index: 8400021 (Open Web Text)

Max Activating Token Index: 312

Text #9

Max Range: 6.4396. Min Range: -6.4396

Max Act: 6.0028. Min Act: -0.1700

Data Index: 3354338 (Open Web Text)

Max Activating Token Index: 905

Text #10

Max Range: 6.4396. Min Range: -6.4396

Max Act: 6.0013. Min Act: -0.1700

Data Index: 3927076 (Open Web Text)

Max Activating Token Index: 1010

Text #11

Max Range: 6.4396. Min Range: -6.4396

Max Act: 5.9527. Min Act: -0.1700

Data Index: 6466485 (Open Web Text)

Max Activating Token Index: 484

Text #12

Max Range: 6.4396. Min Range: -6.4396

Max Act: 5.9276. Min Act: -0.1700

Data Index: 1565755 (Open Web Text)

Max Activating Token Index: 473

Text #13

Max Range: 6.4396. Min Range: -6.4396

Max Act: 5.9372. Min Act: -0.1700

Data Index: 7790620 (Open Web Text)

Max Activating Token Index: 1015

Text #14

Max Range: 6.4396. Min Range: -6.4396

Max Act: 5.9119. Min Act: -0.1700

Data Index: 161917 (Open Web Text)

Max Activating Token Index: 923

Text #15

Max Range: 6.4396. Min Range: -6.4396

Max Act: 5.8605. Min Act: -0.1700

Data Index: 2829200 (Open Web Text)

Max Activating Token Index: 348

Text #16

Max Range: 6.4396. Min Range: -6.4396

Max Act: 5.8965. Min Act: -0.1700

Data Index: 8008229 (Open Web Text)

Max Activating Token Index: 970

Text #17

Max Range: 6.4396. Min Range: -6.4396

Max Act: 5.8870. Min Act: -0.1700

Data Index: 1646720 (Open Web Text)

Max Activating Token Index: 969

Text #18

Max Range: 6.4396. Min Range: -6.4396

Max Act: 5.8925. Min Act: -0.1700

Data Index: 8618445 (Open Web Text)

Max Activating Token Index: 121

Text #19

Max Range: 6.4396. Min Range: -6.4396

Max Act: 5.8431. Min Act: -0.1700

Data Index: 1692683 (Open Web Text)

Max Activating Token Index: 691