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

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

Neuron 267 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: 3.3661. Min Range: -3.3661

Max Act: 3.3661. Min Act: -0.1700

Data Index: 761221 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 3.3661. Min Range: -3.3661

Max Act: 3.3033. Min Act: -0.1700

Data Index: 34237 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 3.3661. Min Range: -3.3661

Max Act: 3.2090. Min Act: -0.1700

Data Index: 161649 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 3.3661. Min Range: -3.3661

Max Act: 3.2090. Min Act: -0.1700

Data Index: 202402 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 3.3661. Min Range: -3.3661

Max Act: 3.1617. Min Act: -0.1700

Data Index: 968984 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 3.3661. Min Range: -3.3661

Max Act: 3.1302. Min Act: -0.1700

Data Index: 365062 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 3.3661. Min Range: -3.3661

Max Act: 3.1302. Min Act: -0.1700

Data Index: 557279 (C4 (Web Text))

Max Activating Token Index: 466

Text #7

Max Range: 3.3661. Min Range: -3.3661

Max Act: 3.1145. Min Act: -0.1700

Data Index: 1228463 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 3.3661. Min Range: -3.3661

Max Act: 3.0987. Min Act: -0.1700

Data Index: 474657 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 3.3661. Min Range: -3.3661

Max Act: 3.0830. Min Act: -0.1700

Data Index: 1042508 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 3.3661. Min Range: -3.3661

Max Act: 3.0987. Min Act: -0.1700

Data Index: 133272 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 3.3661. Min Range: -3.3661

Max Act: 3.0987. Min Act: -0.1700

Data Index: 1350361 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 3.3661. Min Range: -3.3661

Max Act: 3.0987. Min Act: -0.1700

Data Index: 471141 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 3.3661. Min Range: -3.3661

Max Act: 3.0514. Min Act: -0.1700

Data Index: 744270 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 3.3661. Min Range: -3.3661

Max Act: 3.0830. Min Act: -0.1700

Data Index: 1176531 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 3.3661. Min Range: -3.3661

Max Act: 3.0514. Min Act: -0.1700

Data Index: 1532 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 3.3661. Min Range: -3.3661

Max Act: 3.0830. Min Act: -0.1700

Data Index: 726559 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 3.3661. Min Range: -3.3661

Max Act: 3.0514. Min Act: -0.1700

Data Index: 538149 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 3.3661. Min Range: -3.3661

Max Act: 3.0672. Min Act: -0.1700

Data Index: 85681 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 3.3661. Min Range: -3.3661

Max Act: 3.0672. Min Act: -0.1700

Data Index: 608086 (C4 (Web Text))

Max Activating Token Index: 449