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

Dataset: Open Web Text

Neuron 246 in Layer 3

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: 3.5154. Min Range: -3.5154

Max Act: 3.4996. Min Act: -0.1700

Data Index: 7940480 (Open Web Text)

Max Activating Token Index: 567

Text #1

Max Range: 3.5154. Min Range: -3.5154

Max Act: 3.5154. Min Act: -0.1700

Data Index: 7854542 (Open Web Text)

Max Activating Token Index: 389

Text #2

Max Range: 3.5154. Min Range: -3.5154

Max Act: 3.4630. Min Act: -0.1700

Data Index: 7854543 (Open Web Text)

Max Activating Token Index: 478

Text #3

Max Range: 3.5154. Min Range: -3.5154

Max Act: 3.4644. Min Act: -0.1700

Data Index: 1554125 (Open Web Text)

Max Activating Token Index: 868

Text #4

Max Range: 3.5154. Min Range: -3.5154

Max Act: 3.4386. Min Act: -0.1700

Data Index: 4972428 (Open Web Text)

Max Activating Token Index: 868

Text #5

Max Range: 3.5154. Min Range: -3.5154

Max Act: 3.4436. Min Act: -0.1700

Data Index: 8505369 (Open Web Text)

Max Activating Token Index: 644

Text #6

Max Range: 3.5154. Min Range: -3.5154

Max Act: 3.4263. Min Act: -0.1700

Data Index: 706781 (Open Web Text)

Max Activating Token Index: 545

Text #7

Max Range: 3.5154. Min Range: -3.5154

Max Act: 3.4187. Min Act: -0.1700

Data Index: 6139399 (Open Web Text)

Max Activating Token Index: 511

Text #8

Max Range: 3.5154. Min Range: -3.5154

Max Act: 3.4290. Min Act: -0.1700

Data Index: 2380095 (Open Web Text)

Max Activating Token Index: 353

Text #9

Max Range: 3.5154. Min Range: -3.5154

Max Act: 3.4345. Min Act: -0.1700

Data Index: 1999909 (Open Web Text)

Max Activating Token Index: 555

Text #10

Max Range: 3.5154. Min Range: -3.5154

Max Act: 3.4184. Min Act: -0.1700

Data Index: 2302639 (Open Web Text)

Max Activating Token Index: 184

Text #11

Max Range: 3.5154. Min Range: -3.5154

Max Act: 3.4422. Min Act: -0.1700

Data Index: 6729551 (Open Web Text)

Max Activating Token Index: 760

Text #12

Max Range: 3.5154. Min Range: -3.5154

Max Act: 3.3954. Min Act: -0.1700

Data Index: 6612926 (Open Web Text)

Max Activating Token Index: 281

Text #13

Max Range: 3.5154. Min Range: -3.5154

Max Act: 3.3876. Min Act: -0.1700

Data Index: 6615362 (Open Web Text)

Max Activating Token Index: 1020

Text #14

Max Range: 3.5154. Min Range: -3.5154

Max Act: 3.4232. Min Act: -0.1700

Data Index: 3005039 (Open Web Text)

Max Activating Token Index: 86

Text #15

Max Range: 3.5154. Min Range: -3.5154

Max Act: 3.4073. Min Act: -0.1700

Data Index: 639087 (Open Web Text)

Max Activating Token Index: 1014

Text #16

Max Range: 3.5154. Min Range: -3.5154

Max Act: 3.4086. Min Act: -0.1700

Data Index: 3383800 (Open Web Text)

Max Activating Token Index: 615

Text #17

Max Range: 3.5154. Min Range: -3.5154

Max Act: 3.4024. Min Act: -0.1700

Data Index: 773876 (Open Web Text)

Max Activating Token Index: 979

Text #18

Max Range: 3.5154. Min Range: -3.5154

Max Act: 3.4060. Min Act: -0.1700

Data Index: 4622063 (Open Web Text)

Max Activating Token Index: 461

Text #19

Max Range: 3.5154. Min Range: -3.5154

Max Act: 3.3784. Min Act: -0.1700

Data Index: 3925966 (Open Web Text)

Max Activating Token Index: 175