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

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

Neuron 4524 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5326. Min Range: -4.5326

Max Act: 4.5326. Min Act: -0.0000

Data Index: 737026 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 4.5326. Min Range: -4.5326

Max Act: 4.4758. Min Act: -0.0000

Data Index: 296772 (C4 (Web Text))

Max Activating Token Index: 126

Text #2

Max Range: 4.5326. Min Range: -4.5326

Max Act: 3.9387. Min Act: -0.0000

Data Index: 21273 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 4.5326. Min Range: -4.5326

Max Act: 4.1533. Min Act: -0.0000

Data Index: 750209 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 4.5326. Min Range: -4.5326

Max Act: 3.7531. Min Act: -0.0000

Data Index: 20172 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 4.5326. Min Range: -4.5326

Max Act: 3.4943. Min Act: -0.0000

Data Index: 179145 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 4.5326. Min Range: -4.5326

Max Act: 3.4945. Min Act: -0.0000

Data Index: 58834 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 4.5326. Min Range: -4.5326

Max Act: 3.6590. Min Act: -0.0000

Data Index: 55489 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 4.5326. Min Range: -4.5326

Max Act: 3.4947. Min Act: -0.0000

Data Index: 540268 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 4.5326. Min Range: -4.5326

Max Act: 2.6421. Min Act: -0.0000

Data Index: 129998 (C4 (Web Text))

Max Activating Token Index: 226

Text #10

Max Range: 4.5326. Min Range: -4.5326

Max Act: 3.0312. Min Act: -0.0000

Data Index: 1167024 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 4.5326. Min Range: -4.5326

Max Act: 3.1385. Min Act: -0.0000

Data Index: 1133460 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 4.5326. Min Range: -4.5326

Max Act: 2.9350. Min Act: -0.0000

Data Index: 243586 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 4.5326. Min Range: -4.5326

Max Act: 3.0003. Min Act: -0.0000

Data Index: 481710 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 4.5326. Min Range: -4.5326

Max Act: 2.8354. Min Act: -0.0000

Data Index: 1220516 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 4.5326. Min Range: -4.5326

Max Act: 2.7881. Min Act: -0.0000

Data Index: 387566 (C4 (Web Text))

Max Activating Token Index: 438

Text #16

Max Range: 4.5326. Min Range: -4.5326

Max Act: 2.6470. Min Act: -0.0000

Data Index: 1272988 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 4.5326. Min Range: -4.5326

Max Act: 2.7215. Min Act: -0.0000

Data Index: 1047928 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 4.5326. Min Range: -4.5326

Max Act: 2.5687. Min Act: -0.0000

Data Index: 954811 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 4.5326. Min Range: -4.5326

Max Act: 2.5559. Min Act: -0.0000

Data Index: 1325667 (C4 (Web Text))

Max Activating Token Index: 447