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

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

Neuron 2566 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.9980. Min Act: -0.0001

Data Index: 123043 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.8690. Min Act: -0.0001

Data Index: 1237769 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.8871. Min Act: -0.0001

Data Index: 634070 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.8226. Min Act: -0.0001

Data Index: 268143 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.7779. Min Act: -0.0001

Data Index: 745955 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.7312. Min Act: -0.0001

Data Index: 168887 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.7470. Min Act: -0.0001

Data Index: 468142 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.8031. Min Act: -0.0001

Data Index: 1119625 (C4 (Web Text))

Max Activating Token Index: 394

Text #8

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.7997. Min Act: -0.0001

Data Index: 411540 (C4 (Web Text))

Max Activating Token Index: 811

Text #9

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.7395. Min Act: -0.0001

Data Index: 340684 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.7771. Min Act: -0.0001

Data Index: 1040119 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.7773. Min Act: -0.0001

Data Index: 476632 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.6933. Min Act: -0.0001

Data Index: 647246 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.7289. Min Act: -0.0001

Data Index: 976088 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.7056. Min Act: -0.0001

Data Index: 1148409 (C4 (Web Text))

Max Activating Token Index: 325

Text #15

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.7254. Min Act: -0.0001

Data Index: 1018871 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.7265. Min Act: -0.0001

Data Index: 1286537 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.7433. Min Act: -0.0001

Data Index: 1187527 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.7457. Min Act: -0.0001

Data Index: 1070372 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.7222. Min Act: -0.0001

Data Index: 35634 (C4 (Web Text))

Max Activating Token Index: 688