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

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

Neuron 3778 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: 1.4223. Min Range: -1.4223

Max Act: 1.4223. Min Act: -0.0001

Data Index: 1316850 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.3558. Min Act: -0.0001

Data Index: 821111 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.3481. Min Act: -0.0001

Data Index: 1096144 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.3516. Min Act: -0.0001

Data Index: 381325 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.3478. Min Act: -0.0001

Data Index: 653233 (C4 (Web Text))

Max Activating Token Index: 1015

Text #5

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.3748. Min Act: -0.0001

Data Index: 160394 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.3824. Min Act: -0.0001

Data Index: 651451 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.2846. Min Act: -0.0001

Data Index: 1028618 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.3371. Min Act: -0.0001

Data Index: 512641 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.3269. Min Act: -0.0001

Data Index: 402099 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.2250. Min Act: -0.0001

Data Index: 27253 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.2812. Min Act: -0.0001

Data Index: 495461 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.2384. Min Act: -0.0001

Data Index: 1011123 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.3239. Min Act: -0.0001

Data Index: 797329 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.2942. Min Act: -0.0001

Data Index: 1270411 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.2686. Min Act: -0.0001

Data Index: 194464 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.2676. Min Act: -0.0001

Data Index: 236308 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.2169. Min Act: -0.0001

Data Index: 988381 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.2290. Min Act: -0.0001

Data Index: 133855 (C4 (Web Text))

Max Activating Token Index: 452

Text #19

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.2531. Min Act: -0.0001

Data Index: 1191778 (C4 (Web Text))

Max Activating Token Index: 188