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

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

Neuron 5120 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2993. Min Range: -3.2993

Max Act: 3.2993. Min Act: -0.0001

Data Index: 1280000 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 3.2993. Min Range: -3.2993

Max Act: 2.6164. Min Act: -0.0001

Data Index: 860148 (C4 (Web Text))

Max Activating Token Index: 931

Text #2

Max Range: 3.2993. Min Range: -3.2993

Max Act: 2.5966. Min Act: -0.0000

Data Index: 807808 (C4 (Web Text))

Max Activating Token Index: 164

Text #3

Max Range: 3.2993. Min Range: -3.2993

Max Act: 2.3366. Min Act: -0.0001

Data Index: 123911 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 3.2993. Min Range: -3.2993

Max Act: 2.5680. Min Act: -0.0000

Data Index: 1140834 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 3.2993. Min Range: -3.2993

Max Act: 2.2888. Min Act: -0.0000

Data Index: 310043 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 3.2993. Min Range: -3.2993

Max Act: 2.5203. Min Act: -0.0000

Data Index: 590990 (C4 (Web Text))

Max Activating Token Index: 387

Text #7

Max Range: 3.2993. Min Range: -3.2993

Max Act: 2.2446. Min Act: -0.0000

Data Index: 722007 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 3.2993. Min Range: -3.2993

Max Act: 2.3296. Min Act: -0.0001

Data Index: 51501 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 3.2993. Min Range: -3.2993

Max Act: 2.2275. Min Act: -0.0000

Data Index: 1007093 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 3.2993. Min Range: -3.2993

Max Act: 2.2032. Min Act: -0.0001

Data Index: 159984 (C4 (Web Text))

Max Activating Token Index: 139

Text #11

Max Range: 3.2993. Min Range: -3.2993

Max Act: 2.3148. Min Act: -0.0000

Data Index: 598861 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 3.2993. Min Range: -3.2993

Max Act: 2.3684. Min Act: -0.0000

Data Index: 443172 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 3.2993. Min Range: -3.2993

Max Act: 2.2470. Min Act: -0.0001

Data Index: 153390 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 3.2993. Min Range: -3.2993

Max Act: 1.9783. Min Act: -0.0000

Data Index: 610800 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 3.2993. Min Range: -3.2993

Max Act: 2.2417. Min Act: -0.0000

Data Index: 695274 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 3.2993. Min Range: -3.2993

Max Act: 2.1454. Min Act: -0.0000

Data Index: 1157053 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 3.2993. Min Range: -3.2993

Max Act: 2.1136. Min Act: -0.0000

Data Index: 480163 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 3.2993. Min Range: -3.2993

Max Act: 1.9791. Min Act: -0.0000

Data Index: 1240568 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 3.2993. Min Range: -3.2993

Max Act: 1.9926. Min Act: -0.0000

Data Index: 1064211 (C4 (Web Text))

Max Activating Token Index: 321