Model: GELU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 475 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.6459. Min Range: -3.6459

Max Act: 3.6459. Min Act: -0.1700

Data Index: 1239243 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 3.6459. Min Range: -3.6459

Max Act: 3.5520. Min Act: -0.1700

Data Index: 425372 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 3.6459. Min Range: -3.6459

Max Act: 3.5050. Min Act: -0.1700

Data Index: 568191 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 3.6459. Min Range: -3.6459

Max Act: 3.4893. Min Act: -0.1700

Data Index: 1166632 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 3.6459. Min Range: -3.6459

Max Act: 3.4737. Min Act: -0.1700

Data Index: 934673 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 3.6459. Min Range: -3.6459

Max Act: 3.4893. Min Act: -0.1700

Data Index: 443837 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 3.6459. Min Range: -3.6459

Max Act: 3.4580. Min Act: -0.1700

Data Index: 543777 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 3.6459. Min Range: -3.6459

Max Act: 3.4266. Min Act: -0.1700

Data Index: 81303 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 3.6459. Min Range: -3.6459

Max Act: 3.3953. Min Act: -0.1700

Data Index: 205381 (C4 (Web Text))

Max Activating Token Index: 432

Text #9

Max Range: 3.6459. Min Range: -3.6459

Max Act: 3.4266. Min Act: -0.1700

Data Index: 1236325 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 3.6459. Min Range: -3.6459

Max Act: 3.3796. Min Act: -0.1700

Data Index: 1227596 (C4 (Web Text))

Max Activating Token Index: 934

Text #11

Max Range: 3.6459. Min Range: -3.6459

Max Act: 3.4423. Min Act: -0.1700

Data Index: 1259447 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 3.6459. Min Range: -3.6459

Max Act: 3.4110. Min Act: -0.1700

Data Index: 440438 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 3.6459. Min Range: -3.6459

Max Act: 3.3796. Min Act: -0.1700

Data Index: 700519 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 3.6459. Min Range: -3.6459

Max Act: 3.3953. Min Act: -0.1700

Data Index: 1346175 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 3.6459. Min Range: -3.6459

Max Act: 3.3639. Min Act: -0.1700

Data Index: 1172273 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 3.6459. Min Range: -3.6459

Max Act: 3.4110. Min Act: -0.1700

Data Index: 281130 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 3.6459. Min Range: -3.6459

Max Act: 3.3953. Min Act: -0.1700

Data Index: 339819 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 3.6459. Min Range: -3.6459

Max Act: 3.3796. Min Act: -0.1700

Data Index: 861304 (C4 (Web Text))

Max Activating Token Index: 350

Text #19

Max Range: 3.6459. Min Range: -3.6459

Max Act: 3.4580. Min Act: -0.1700

Data Index: 1216351 (C4 (Web Text))

Max Activating Token Index: 476