Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2923 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4118. Min Range: -1.4118

Max Act: 1.3559. Min Act: -0.0000

Data Index: 933689 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 1.4118. Min Range: -1.4118

Max Act: 1.3399. Min Act: -0.0000

Data Index: 933406 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 1.4118. Min Range: -1.4118

Max Act: 1.4060. Min Act: -0.0000

Data Index: 155414 (C4 (Web Text))

Max Activating Token Index: 562

Text #3

Max Range: 1.4118. Min Range: -1.4118

Max Act: 1.4118. Min Act: -0.0000

Data Index: 1141723 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 1.4118. Min Range: -1.4118

Max Act: 1.3138. Min Act: 0.0000

Data Index: 693451 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 1.4118. Min Range: -1.4118

Max Act: 1.2507. Min Act: -0.0000

Data Index: 347214 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 1.4118. Min Range: -1.4118

Max Act: 1.2019. Min Act: -0.0000

Data Index: 403298 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 1.4118. Min Range: -1.4118

Max Act: 1.2726. Min Act: -0.0000

Data Index: 811955 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 1.4118. Min Range: -1.4118

Max Act: 1.1361. Min Act: -0.0000

Data Index: 1164402 (C4 (Web Text))

Max Activating Token Index: 359

Text #9

Max Range: 1.4118. Min Range: -1.4118

Max Act: 1.2647. Min Act: -0.0000

Data Index: 265731 (C4 (Web Text))

Max Activating Token Index: 872

Text #10

Max Range: 1.4118. Min Range: -1.4118

Max Act: 1.2281. Min Act: -0.0000

Data Index: 487091 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 1.4118. Min Range: -1.4118

Max Act: 1.2205. Min Act: -0.0000

Data Index: 934773 (C4 (Web Text))

Max Activating Token Index: 801

Text #12

Max Range: 1.4118. Min Range: -1.4118

Max Act: 1.2205. Min Act: -0.0000

Data Index: 919370 (C4 (Web Text))

Max Activating Token Index: 68

Text #13

Max Range: 1.4118. Min Range: -1.4118

Max Act: 1.2164. Min Act: -0.0000

Data Index: 757213 (C4 (Web Text))

Max Activating Token Index: 762

Text #14

Max Range: 1.4118. Min Range: -1.4118

Max Act: 1.1984. Min Act: -0.0000

Data Index: 517130 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 1.4118. Min Range: -1.4118

Max Act: 1.2023. Min Act: -0.0000

Data Index: 1172093 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 1.4118. Min Range: -1.4118

Max Act: 1.1973. Min Act: -0.0000

Data Index: 726885 (C4 (Web Text))

Max Activating Token Index: 387

Text #17

Max Range: 1.4118. Min Range: -1.4118

Max Act: 1.2075. Min Act: -0.0000

Data Index: 200743 (C4 (Web Text))

Max Activating Token Index: 799

Text #18

Max Range: 1.4118. Min Range: -1.4118

Max Act: 1.1232. Min Act: -0.0000

Data Index: 697673 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 1.4118. Min Range: -1.4118

Max Act: 1.1897. Min Act: -0.0000

Data Index: 1316173 (C4 (Web Text))

Max Activating Token Index: 690