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

Dataset: Open Web Text

Neuron 2169 in Layer 2

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: 3.4965. Min Range: -3.4965

Max Act: 3.4965. Min Act: -0.1700

Data Index: 1861860 (Open Web Text)

Max Activating Token Index: 643

Text #1

Max Range: 3.4965. Min Range: -3.4965

Max Act: 3.4426. Min Act: -0.1700

Data Index: 4512980 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 3.4965. Min Range: -3.4965

Max Act: 3.4417. Min Act: -0.1700

Data Index: 1969701 (Open Web Text)

Max Activating Token Index: 268

Text #3

Max Range: 3.4965. Min Range: -3.4965

Max Act: 3.3955. Min Act: -0.1700

Data Index: 6130064 (Open Web Text)

Max Activating Token Index: 410

Text #4

Max Range: 3.4965. Min Range: -3.4965

Max Act: 3.4034. Min Act: -0.1700

Data Index: 4643656 (Open Web Text)

Max Activating Token Index: 479

Text #5

Max Range: 3.4965. Min Range: -3.4965

Max Act: 3.3941. Min Act: -0.1700

Data Index: 3374052 (Open Web Text)

Max Activating Token Index: 955

Text #6

Max Range: 3.4965. Min Range: -3.4965

Max Act: 3.4259. Min Act: -0.1700

Data Index: 8500371 (Open Web Text)

Max Activating Token Index: 441

Text #7

Max Range: 3.4965. Min Range: -3.4965

Max Act: 3.3732. Min Act: -0.1700

Data Index: 2511263 (Open Web Text)

Max Activating Token Index: 430

Text #8

Max Range: 3.4965. Min Range: -3.4965

Max Act: 3.3627. Min Act: -0.1700

Data Index: 3940770 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 3.4965. Min Range: -3.4965

Max Act: 3.3639. Min Act: -0.1700

Data Index: 2092615 (Open Web Text)

Max Activating Token Index: 140

Text #10

Max Range: 3.4965. Min Range: -3.4965

Max Act: 3.3327. Min Act: -0.1700

Data Index: 239411 (Open Web Text)

Max Activating Token Index: 44

Text #11

Max Range: 3.4965. Min Range: -3.4965

Max Act: 3.3237. Min Act: -0.1700

Data Index: 8769239 (Open Web Text)

Max Activating Token Index: 222

Text #12

Max Range: 3.4965. Min Range: -3.4965

Max Act: 3.3154. Min Act: -0.1700

Data Index: 1209438 (Open Web Text)

Max Activating Token Index: 14

Text #13

Max Range: 3.4965. Min Range: -3.4965

Max Act: 3.3191. Min Act: -0.1700

Data Index: 1332984 (Open Web Text)

Max Activating Token Index: 27

Text #14

Max Range: 3.4965. Min Range: -3.4965

Max Act: 3.3183. Min Act: -0.1700

Data Index: 6109912 (Open Web Text)

Max Activating Token Index: 91

Text #15

Max Range: 3.4965. Min Range: -3.4965

Max Act: 3.3211. Min Act: -0.1700

Data Index: 8336232 (Open Web Text)

Max Activating Token Index: 314

Text #16

Max Range: 3.4965. Min Range: -3.4965

Max Act: 3.3060. Min Act: -0.1700

Data Index: 7398448 (Open Web Text)

Max Activating Token Index: 618

Text #17

Max Range: 3.4965. Min Range: -3.4965

Max Act: 3.3186. Min Act: -0.1700

Data Index: 6924225 (Open Web Text)

Max Activating Token Index: 218

Text #18

Max Range: 3.4965. Min Range: -3.4965

Max Act: 3.2932. Min Act: -0.1700

Data Index: 3559390 (Open Web Text)

Max Activating Token Index: 471

Text #19

Max Range: 3.4965. Min Range: -3.4965

Max Act: 3.3041. Min Act: -0.1700

Data Index: 8309978 (Open Web Text)

Max Activating Token Index: 169