Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3929 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5734. Min Range: -0.5734

Max Act: 0.5734. Min Act: -0.0000

Data Index: 760512 (C4 (Web Text))

Max Activating Token Index: 672

Text #1

Max Range: 0.5734. Min Range: -0.5734

Max Act: 0.4851. Min Act: -0.0000

Data Index: 633528 (C4 (Web Text))

Max Activating Token Index: 224

Text #2

Max Range: 0.5734. Min Range: -0.5734

Max Act: 0.4886. Min Act: -0.0000

Data Index: 506602 (C4 (Web Text))

Max Activating Token Index: 398

Text #3

Max Range: 0.5734. Min Range: -0.5734

Max Act: 0.4712. Min Act: -0.0000

Data Index: 31068 (C4 (Web Text))

Max Activating Token Index: 420

Text #4

Max Range: 0.5734. Min Range: -0.5734

Max Act: 0.4832. Min Act: -0.0000

Data Index: 1306142 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 0.5734. Min Range: -0.5734

Max Act: 0.4388. Min Act: -0.0000

Data Index: 829781 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 0.5734. Min Range: -0.5734

Max Act: 0.4337. Min Act: -0.0000

Data Index: 836421 (C4 (Web Text))

Max Activating Token Index: 552

Text #7

Max Range: 0.5734. Min Range: -0.5734

Max Act: 0.4377. Min Act: -0.0000

Data Index: 555023 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 0.5734. Min Range: -0.5734

Max Act: 0.4272. Min Act: -0.0000

Data Index: 883277 (C4 (Web Text))

Max Activating Token Index: 859

Text #9

Max Range: 0.5734. Min Range: -0.5734

Max Act: 0.4377. Min Act: -0.0000

Data Index: 1128262 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 0.5734. Min Range: -0.5734

Max Act: 0.4326. Min Act: -0.0000

Data Index: 808708 (C4 (Web Text))

Max Activating Token Index: 147

Text #11

Max Range: 0.5734. Min Range: -0.5734

Max Act: 0.4141. Min Act: -0.0000

Data Index: 309140 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 0.5734. Min Range: -0.5734

Max Act: 0.4081. Min Act: -0.0000

Data Index: 1053456 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 0.5734. Min Range: -0.5734

Max Act: 0.3775. Min Act: -0.0000

Data Index: 654679 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 0.5734. Min Range: -0.5734

Max Act: 0.3238. Min Act: -0.0000

Data Index: 1301130 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 0.5734. Min Range: -0.5734

Max Act: 0.3758. Min Act: -0.0000

Data Index: 433286 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 0.5734. Min Range: -0.5734

Max Act: 0.3612. Min Act: -0.0000

Data Index: 43703 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 0.5734. Min Range: -0.5734

Max Act: 0.3876. Min Act: -0.0000

Data Index: 437244 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 0.5734. Min Range: -0.5734

Max Act: 0.3790. Min Act: -0.0000

Data Index: 1308589 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 0.5734. Min Range: -0.5734

Max Act: 0.3461. Min Act: -0.0000

Data Index: 528493 (C4 (Web Text))

Max Activating Token Index: 98