Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3146 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.4987. Min Act: -0.0001

Data Index: 454305 (C4 (Web Text))

Max Activating Token Index: 213

Text #1

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.4184. Min Act: -0.0000

Data Index: 151752 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.4104. Min Act: -0.0000

Data Index: 824110 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.4045. Min Act: -0.0000

Data Index: 985861 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.4181. Min Act: -0.0000

Data Index: 1046482 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3828. Min Act: -0.0000

Data Index: 267351 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3925. Min Act: -0.0000

Data Index: 1271452 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.4057. Min Act: -0.0000

Data Index: 556088 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3689. Min Act: -0.0000

Data Index: 933025 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3637. Min Act: -0.0000

Data Index: 85759 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3754. Min Act: -0.0001

Data Index: 104435 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3622. Min Act: -0.0000

Data Index: 932789 (C4 (Web Text))

Max Activating Token Index: 955

Text #12

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3604. Min Act: -0.0000

Data Index: 994204 (C4 (Web Text))

Max Activating Token Index: 337

Text #13

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3471. Min Act: -0.0000

Data Index: 910813 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3559. Min Act: -0.0000

Data Index: 1191474 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3393. Min Act: -0.0000

Data Index: 510288 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3373. Min Act: -0.0001

Data Index: 840265 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3210. Min Act: -0.0000

Data Index: 516993 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3482. Min Act: -0.0001

Data Index: 182188 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3197. Min Act: -0.0000

Data Index: 1308892 (C4 (Web Text))

Max Activating Token Index: 598