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

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

Neuron 628 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: 4.4207. Min Range: -4.4207

Max Act: 4.4207. Min Act: -0.0000

Data Index: 881315 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 4.4207. Min Range: -4.4207

Max Act: 4.2723. Min Act: -0.0000

Data Index: 847676 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 4.4207. Min Range: -4.4207

Max Act: 3.7272. Min Act: -0.0000

Data Index: 241400 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 4.4207. Min Range: -4.4207

Max Act: 3.6971. Min Act: -0.0000

Data Index: 1312904 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 4.4207. Min Range: -4.4207

Max Act: 3.8324. Min Act: -0.0000

Data Index: 826199 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 4.4207. Min Range: -4.4207

Max Act: 3.5513. Min Act: -0.0000

Data Index: 143060 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 4.4207. Min Range: -4.4207

Max Act: 3.5213. Min Act: -0.0000

Data Index: 897769 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 4.4207. Min Range: -4.4207

Max Act: 3.2472. Min Act: -0.0000

Data Index: 1198558 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 4.4207. Min Range: -4.4207

Max Act: 3.0705. Min Act: -0.0000

Data Index: 381025 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 4.4207. Min Range: -4.4207

Max Act: 3.0055. Min Act: -0.0000

Data Index: 887829 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 4.4207. Min Range: -4.4207

Max Act: 3.1377. Min Act: -0.0000

Data Index: 32071 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 4.4207. Min Range: -4.4207

Max Act: 3.0017. Min Act: -0.0000

Data Index: 1269887 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 4.4207. Min Range: -4.4207

Max Act: 3.2987. Min Act: -0.0000

Data Index: 173502 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 4.4207. Min Range: -4.4207

Max Act: 3.1176. Min Act: -0.0000

Data Index: 424595 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 4.4207. Min Range: -4.4207

Max Act: 3.1006. Min Act: -0.0000

Data Index: 649251 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 4.4207. Min Range: -4.4207

Max Act: 2.6933. Min Act: -0.0000

Data Index: 4334 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 4.4207. Min Range: -4.4207

Max Act: 3.3147. Min Act: -0.0000

Data Index: 1344637 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 4.4207. Min Range: -4.4207

Max Act: 2.9402. Min Act: -0.0000

Data Index: 1266729 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 4.4207. Min Range: -4.4207

Max Act: 2.9464. Min Act: -0.0000

Data Index: 984831 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 4.4207. Min Range: -4.4207

Max Act: 2.9048. Min Act: -0.0000

Data Index: 1309965 (C4 (Web Text))

Max Activating Token Index: 87