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

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

Neuron 4047 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2659. Min Act: -0.0002

Data Index: 1091716 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2533. Min Act: -0.0001

Data Index: 1161732 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2343. Min Act: -0.0001

Data Index: 509376 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2490. Min Act: -0.0002

Data Index: 1316518 (C4 (Web Text))

Max Activating Token Index: 296

Text #4

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2470. Min Act: -0.0002

Data Index: 994181 (C4 (Web Text))

Max Activating Token Index: 773

Text #5

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2365. Min Act: -0.0002

Data Index: 484457 (C4 (Web Text))

Max Activating Token Index: 542

Text #6

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2294. Min Act: -0.0002

Data Index: 1157932 (C4 (Web Text))

Max Activating Token Index: 473

Text #7

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2063. Min Act: -0.0002

Data Index: 682892 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2048. Min Act: -0.0002

Data Index: 859152 (C4 (Web Text))

Max Activating Token Index: 341

Text #9

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2006. Min Act: -0.0002

Data Index: 1133820 (C4 (Web Text))

Max Activating Token Index: 403

Text #10

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2085. Min Act: -0.0002

Data Index: 1271105 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2045. Min Act: -0.0002

Data Index: 461161 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1960. Min Act: -0.0001

Data Index: 451020 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1942. Min Act: -0.0001

Data Index: 148347 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1942. Min Act: -0.0002

Data Index: 417606 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2005. Min Act: -0.0002

Data Index: 1253338 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2058. Min Act: -0.0002

Data Index: 586597 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2042. Min Act: -0.0001

Data Index: 1198093 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1888. Min Act: -0.0002

Data Index: 588048 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2026. Min Act: -0.0002

Data Index: 167604 (C4 (Web Text))

Max Activating Token Index: 355