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

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

Neuron 891 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5123. Min Range: -0.5123

Max Act: 0.5123. Min Act: -0.0001

Data Index: 242758 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 0.5123. Min Range: -0.5123

Max Act: 0.3930. Min Act: -0.0001

Data Index: 1169324 (C4 (Web Text))

Max Activating Token Index: 652

Text #2

Max Range: 0.5123. Min Range: -0.5123

Max Act: 0.4890. Min Act: -0.0001

Data Index: 567219 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 0.5123. Min Range: -0.5123

Max Act: 0.4131. Min Act: -0.0001

Data Index: 902591 (C4 (Web Text))

Max Activating Token Index: 525

Text #4

Max Range: 0.5123. Min Range: -0.5123

Max Act: 0.4140. Min Act: -0.0001

Data Index: 1326944 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 0.5123. Min Range: -0.5123

Max Act: 0.4694. Min Act: -0.0001

Data Index: 212973 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 0.5123. Min Range: -0.5123

Max Act: 0.4389. Min Act: -0.0001

Data Index: 928319 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 0.5123. Min Range: -0.5123

Max Act: 0.3974. Min Act: -0.0001

Data Index: 557038 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 0.5123. Min Range: -0.5123

Max Act: 0.4609. Min Act: -0.0001

Data Index: 989723 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 0.5123. Min Range: -0.5123

Max Act: 0.4566. Min Act: -0.0001

Data Index: 576490 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 0.5123. Min Range: -0.5123

Max Act: 0.4378. Min Act: -0.0001

Data Index: 910755 (C4 (Web Text))

Max Activating Token Index: 139

Text #11

Max Range: 0.5123. Min Range: -0.5123

Max Act: 0.4253. Min Act: -0.0001

Data Index: 203917 (C4 (Web Text))

Max Activating Token Index: 225

Text #12

Max Range: 0.5123. Min Range: -0.5123

Max Act: 0.4476. Min Act: -0.0001

Data Index: 1192750 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 0.5123. Min Range: -0.5123

Max Act: 0.3837. Min Act: -0.0001

Data Index: 434662 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 0.5123. Min Range: -0.5123

Max Act: 0.4091. Min Act: -0.0001

Data Index: 966228 (C4 (Web Text))

Max Activating Token Index: 999

Text #15

Max Range: 0.5123. Min Range: -0.5123

Max Act: 0.4078. Min Act: -0.0001

Data Index: 1164352 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 0.5123. Min Range: -0.5123

Max Act: 0.4011. Min Act: -0.0001

Data Index: 474141 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 0.5123. Min Range: -0.5123

Max Act: 0.4386. Min Act: -0.0001

Data Index: 731190 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 0.5123. Min Range: -0.5123

Max Act: 0.4336. Min Act: -0.0001

Data Index: 87409 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 0.5123. Min Range: -0.5123

Max Act: 0.4779. Min Act: -0.0001

Data Index: 629429 (C4 (Web Text))

Max Activating Token Index: 345