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

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

Neuron 5196 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5178. Min Range: -2.5178

Max Act: 2.5178. Min Act: -0.0000

Data Index: 70033 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 2.5178. Min Range: -2.5178

Max Act: 2.2666. Min Act: -0.0000

Data Index: 1022741 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 2.5178. Min Range: -2.5178

Max Act: 2.1400. Min Act: -0.0000

Data Index: 150856 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 2.5178. Min Range: -2.5178

Max Act: 2.1023. Min Act: -0.0000

Data Index: 452190 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 2.5178. Min Range: -2.5178

Max Act: 1.9631. Min Act: -0.0001

Data Index: 384998 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 2.5178. Min Range: -2.5178

Max Act: 2.0469. Min Act: -0.0001

Data Index: 759935 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 2.5178. Min Range: -2.5178

Max Act: 1.9855. Min Act: -0.0001

Data Index: 687298 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 2.5178. Min Range: -2.5178

Max Act: 1.9049. Min Act: -0.0000

Data Index: 64536 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 2.5178. Min Range: -2.5178

Max Act: 1.9535. Min Act: -0.0001

Data Index: 36318 (C4 (Web Text))

Max Activating Token Index: 523

Text #9

Max Range: 2.5178. Min Range: -2.5178

Max Act: 2.0573. Min Act: -0.0000

Data Index: 68159 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 2.5178. Min Range: -2.5178

Max Act: 2.0580. Min Act: -0.0001

Data Index: 711923 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 2.5178. Min Range: -2.5178

Max Act: 2.0437. Min Act: -0.0000

Data Index: 812086 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 2.5178. Min Range: -2.5178

Max Act: 1.8074. Min Act: -0.0000

Data Index: 177477 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 2.5178. Min Range: -2.5178

Max Act: 1.9287. Min Act: -0.0000

Data Index: 1008563 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 2.5178. Min Range: -2.5178

Max Act: 1.9158. Min Act: -0.0000

Data Index: 1043444 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 2.5178. Min Range: -2.5178

Max Act: 1.9190. Min Act: -0.0000

Data Index: 1201063 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 2.5178. Min Range: -2.5178

Max Act: 1.7090. Min Act: -0.0001

Data Index: 151491 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 2.5178. Min Range: -2.5178

Max Act: 1.8919. Min Act: -0.0000

Data Index: 352904 (C4 (Web Text))

Max Activating Token Index: 135

Text #18

Max Range: 2.5178. Min Range: -2.5178

Max Act: 1.7820. Min Act: -0.0000

Data Index: 640685 (C4 (Web Text))

Max Activating Token Index: 652

Text #19

Max Range: 2.5178. Min Range: -2.5178

Max Act: 1.7788. Min Act: -0.0000

Data Index: 1320051 (C4 (Web Text))

Max Activating Token Index: 580