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

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

Neuron 416 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3612. Min Range: -1.3612

Max Act: 1.3612. Min Act: -0.0001

Data Index: 1160148 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 1.3612. Min Range: -1.3612

Max Act: 1.3469. Min Act: -0.0001

Data Index: 496733 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 1.3612. Min Range: -1.3612

Max Act: 1.1312. Min Act: -0.0001

Data Index: 535111 (C4 (Web Text))

Max Activating Token Index: 472

Text #3

Max Range: 1.3612. Min Range: -1.3612

Max Act: 1.1370. Min Act: -0.0001

Data Index: 363764 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 1.3612. Min Range: -1.3612

Max Act: 1.1286. Min Act: -0.0001

Data Index: 150437 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 1.3612. Min Range: -1.3612

Max Act: 1.0610. Min Act: -0.0001

Data Index: 162250 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 1.3612. Min Range: -1.3612

Max Act: 1.0233. Min Act: -0.0001

Data Index: 754002 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 1.3612. Min Range: -1.3612

Max Act: 1.0389. Min Act: -0.0001

Data Index: 491905 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 1.3612. Min Range: -1.3612

Max Act: 1.0687. Min Act: -0.0001

Data Index: 446163 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 1.3612. Min Range: -1.3612

Max Act: 0.9968. Min Act: -0.0001

Data Index: 374734 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 1.3612. Min Range: -1.3612

Max Act: 0.9913. Min Act: -0.0001

Data Index: 394512 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 1.3612. Min Range: -1.3612

Max Act: 1.0154. Min Act: -0.0001

Data Index: 659992 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 1.3612. Min Range: -1.3612

Max Act: 0.9293. Min Act: -0.0001

Data Index: 453028 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 1.3612. Min Range: -1.3612

Max Act: 0.9172. Min Act: -0.0001

Data Index: 876988 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 1.3612. Min Range: -1.3612

Max Act: 0.9460. Min Act: -0.0001

Data Index: 863429 (C4 (Web Text))

Max Activating Token Index: 855

Text #15

Max Range: 1.3612. Min Range: -1.3612

Max Act: 0.8705. Min Act: -0.0001

Data Index: 1278190 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 1.3612. Min Range: -1.3612

Max Act: 0.8906. Min Act: -0.0001

Data Index: 1231597 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 1.3612. Min Range: -1.3612

Max Act: 0.8752. Min Act: -0.0001

Data Index: 935347 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 1.3612. Min Range: -1.3612

Max Act: 0.9596. Min Act: -0.0001

Data Index: 385131 (C4 (Web Text))

Max Activating Token Index: 983

Text #19

Max Range: 1.3612. Min Range: -1.3612

Max Act: 0.8487. Min Act: -0.0001

Data Index: 12068 (C4 (Web Text))

Max Activating Token Index: 105