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

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

Neuron 2623 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0337. Min Range: -1.0337

Max Act: 1.0337. Min Act: -0.0001

Data Index: 256758 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 1.0337. Min Range: -1.0337

Max Act: 1.0302. Min Act: -0.0001

Data Index: 808695 (C4 (Web Text))

Max Activating Token Index: 238

Text #2

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.9777. Min Act: -0.0001

Data Index: 456447 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.9424. Min Act: -0.0001

Data Index: 1296059 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.9418. Min Act: -0.0001

Data Index: 166391 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.9396. Min Act: -0.0001

Data Index: 272365 (C4 (Web Text))

Max Activating Token Index: 889

Text #6

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.9203. Min Act: -0.0001

Data Index: 1192595 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.8953. Min Act: -0.0001

Data Index: 1203008 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.8958. Min Act: -0.0001

Data Index: 158445 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.8864. Min Act: -0.0001

Data Index: 23296 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.9041. Min Act: -0.0001

Data Index: 719688 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.8372. Min Act: -0.0001

Data Index: 417993 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.8376. Min Act: -0.0001

Data Index: 355127 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.8219. Min Act: -0.0001

Data Index: 487768 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.8158. Min Act: -0.0001

Data Index: 912065 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.8320. Min Act: -0.0001

Data Index: 738090 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.8063. Min Act: -0.0001

Data Index: 775794 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.7371. Min Act: -0.0001

Data Index: 881922 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.7653. Min Act: -0.0001

Data Index: 762052 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.7605. Min Act: -0.0001

Data Index: 263275 (C4 (Web Text))

Max Activating Token Index: 73