Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1520 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1672. Min Range: -2.1672

Max Act: 2.1154. Min Act: -0.0000

Data Index: 1334281 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 2.1672. Min Range: -2.1672

Max Act: 2.1672. Min Act: -0.0000

Data Index: 175703 (C4 (Web Text))

Max Activating Token Index: 532

Text #2

Max Range: 2.1672. Min Range: -2.1672

Max Act: 2.1067. Min Act: -0.0000

Data Index: 1152253 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 2.1672. Min Range: -2.1672

Max Act: 2.0084. Min Act: -0.0000

Data Index: 382368 (C4 (Web Text))

Max Activating Token Index: 979

Text #4

Max Range: 2.1672. Min Range: -2.1672

Max Act: 2.0956. Min Act: -0.0000

Data Index: 1331453 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 2.1672. Min Range: -2.1672

Max Act: 2.0687. Min Act: -0.0000

Data Index: 127226 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 2.1672. Min Range: -2.1672

Max Act: 2.0878. Min Act: -0.0000

Data Index: 863746 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 2.1672. Min Range: -2.1672

Max Act: 1.8557. Min Act: -0.0000

Data Index: 857660 (C4 (Web Text))

Max Activating Token Index: 748

Text #8

Max Range: 2.1672. Min Range: -2.1672

Max Act: 1.9572. Min Act: -0.0000

Data Index: 971338 (C4 (Web Text))

Max Activating Token Index: 494

Text #9

Max Range: 2.1672. Min Range: -2.1672

Max Act: 1.9046. Min Act: -0.0000

Data Index: 104390 (C4 (Web Text))

Max Activating Token Index: 567

Text #10

Max Range: 2.1672. Min Range: -2.1672

Max Act: 1.8339. Min Act: -0.0000

Data Index: 148632 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 2.1672. Min Range: -2.1672

Max Act: 1.7224. Min Act: -0.0000

Data Index: 445073 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 2.1672. Min Range: -2.1672

Max Act: 1.8095. Min Act: -0.0000

Data Index: 492609 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 2.1672. Min Range: -2.1672

Max Act: 1.7863. Min Act: -0.0000

Data Index: 920733 (C4 (Web Text))

Max Activating Token Index: 641

Text #14

Max Range: 2.1672. Min Range: -2.1672

Max Act: 1.8051. Min Act: -0.0000

Data Index: 205900 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 2.1672. Min Range: -2.1672

Max Act: 1.8685. Min Act: -0.0000

Data Index: 1293695 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 2.1672. Min Range: -2.1672

Max Act: 1.7397. Min Act: -0.0000

Data Index: 125301 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 2.1672. Min Range: -2.1672

Max Act: 1.7387. Min Act: -0.0000

Data Index: 1001508 (C4 (Web Text))

Max Activating Token Index: 535

Text #18

Max Range: 2.1672. Min Range: -2.1672

Max Act: 1.7332. Min Act: -0.0000

Data Index: 384734 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 2.1672. Min Range: -2.1672

Max Act: 1.6284. Min Act: -0.0000

Data Index: 371961 (C4 (Web Text))

Max Activating Token Index: 102