Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 488 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.7232. Min Act: -0.0004

Data Index: 622368 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.6778. Min Act: -0.0004

Data Index: 289432 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.6789. Min Act: -0.0004

Data Index: 958552 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.6660. Min Act: -0.0004

Data Index: 250439 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.6607. Min Act: -0.0004

Data Index: 626105 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.6539. Min Act: -0.0004

Data Index: 283066 (C4 (Web Text))

Max Activating Token Index: 933

Text #6

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.6335. Min Act: -0.0004

Data Index: 797186 (C4 (Web Text))

Max Activating Token Index: 850

Text #7

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.6946. Min Act: -0.0004

Data Index: 1298691 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.6166. Min Act: -0.0004

Data Index: 202629 (C4 (Web Text))

Max Activating Token Index: 869

Text #9

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.6643. Min Act: -0.0004

Data Index: 104844 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.6618. Min Act: -0.0004

Data Index: 1208476 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.6847. Min Act: -0.0004

Data Index: 294710 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.6797. Min Act: -0.0004

Data Index: 714296 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.6568. Min Act: -0.0004

Data Index: 1233685 (C4 (Web Text))

Max Activating Token Index: 895

Text #14

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.6133. Min Act: -0.0004

Data Index: 689022 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.6912. Min Act: -0.0004

Data Index: 579092 (C4 (Web Text))

Max Activating Token Index: 360

Text #16

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.6685. Min Act: -0.0004

Data Index: 202513 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.6139. Min Act: -0.0004

Data Index: 436594 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.6067. Min Act: -0.0004

Data Index: 450191 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.6279. Min Act: -0.0004

Data Index: 954822 (C4 (Web Text))

Max Activating Token Index: 257