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

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

Neuron 2053 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: 0.4223. Min Range: -0.4223

Max Act: 0.4223. Min Act: -0.0001

Data Index: 260956 (C4 (Web Text))

Max Activating Token Index: 828

Text #1

Max Range: 0.4223. Min Range: -0.4223

Max Act: 0.4218. Min Act: -0.0001

Data Index: 1102165 (C4 (Web Text))

Max Activating Token Index: 205

Text #2

Max Range: 0.4223. Min Range: -0.4223

Max Act: 0.4036. Min Act: -0.0001

Data Index: 749123 (C4 (Web Text))

Max Activating Token Index: 934

Text #3

Max Range: 0.4223. Min Range: -0.4223

Max Act: 0.3981. Min Act: -0.0001

Data Index: 86705 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 0.4223. Min Range: -0.4223

Max Act: 0.3989. Min Act: -0.0001

Data Index: 1186921 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 0.4223. Min Range: -0.4223

Max Act: 0.4082. Min Act: -0.0001

Data Index: 42607 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 0.4223. Min Range: -0.4223

Max Act: 0.3900. Min Act: -0.0001

Data Index: 1174606 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 0.4223. Min Range: -0.4223

Max Act: 0.3866. Min Act: -0.0001

Data Index: 1244857 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 0.4223. Min Range: -0.4223

Max Act: 0.4013. Min Act: -0.0001

Data Index: 1097530 (C4 (Web Text))

Max Activating Token Index: 819

Text #9

Max Range: 0.4223. Min Range: -0.4223

Max Act: 0.3737. Min Act: -0.0001

Data Index: 923246 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 0.4223. Min Range: -0.4223

Max Act: 0.3991. Min Act: -0.0001

Data Index: 911829 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 0.4223. Min Range: -0.4223

Max Act: 0.3557. Min Act: -0.0001

Data Index: 496416 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 0.4223. Min Range: -0.4223

Max Act: 0.3750. Min Act: -0.0001

Data Index: 840872 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 0.4223. Min Range: -0.4223

Max Act: 0.3667. Min Act: -0.0001

Data Index: 732676 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 0.4223. Min Range: -0.4223

Max Act: 0.3586. Min Act: -0.0001

Data Index: 1264207 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 0.4223. Min Range: -0.4223

Max Act: 0.3700. Min Act: -0.0001

Data Index: 957996 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 0.4223. Min Range: -0.4223

Max Act: 0.3582. Min Act: -0.0001

Data Index: 1015435 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 0.4223. Min Range: -0.4223

Max Act: 0.3577. Min Act: -0.0001

Data Index: 148979 (C4 (Web Text))

Max Activating Token Index: 669

Text #18

Max Range: 0.4223. Min Range: -0.4223

Max Act: 0.3442. Min Act: -0.0001

Data Index: 697356 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 0.4223. Min Range: -0.4223

Max Act: 0.3461. Min Act: -0.0001

Data Index: 262118 (C4 (Web Text))

Max Activating Token Index: 576