Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4532 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4125. Min Range: -1.4125

Max Act: 1.4125. Min Act: -0.0001

Data Index: 606382 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 1.4125. Min Range: -1.4125

Max Act: 1.2884. Min Act: -0.0001

Data Index: 445812 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 1.4125. Min Range: -1.4125

Max Act: 1.0719. Min Act: -0.0001

Data Index: 395533 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 1.4125. Min Range: -1.4125

Max Act: 1.0197. Min Act: -0.0001

Data Index: 998120 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 1.4125. Min Range: -1.4125

Max Act: 1.1377. Min Act: -0.0001

Data Index: 699469 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 1.4125. Min Range: -1.4125

Max Act: 1.0708. Min Act: -0.0001

Data Index: 267346 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 1.4125. Min Range: -1.4125

Max Act: 1.1902. Min Act: -0.0001

Data Index: 532567 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 1.4125. Min Range: -1.4125

Max Act: 0.9456. Min Act: -0.0001

Data Index: 1221848 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 1.4125. Min Range: -1.4125

Max Act: 0.9747. Min Act: -0.0001

Data Index: 646544 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 1.4125. Min Range: -1.4125

Max Act: 1.0089. Min Act: -0.0001

Data Index: 253135 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 1.4125. Min Range: -1.4125

Max Act: 0.9438. Min Act: -0.0001

Data Index: 115676 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 1.4125. Min Range: -1.4125

Max Act: 0.9408. Min Act: -0.0001

Data Index: 1105948 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 1.4125. Min Range: -1.4125

Max Act: 0.9223. Min Act: -0.0001

Data Index: 1214081 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 1.4125. Min Range: -1.4125

Max Act: 0.9833. Min Act: -0.0001

Data Index: 214024 (C4 (Web Text))

Max Activating Token Index: 711

Text #14

Max Range: 1.4125. Min Range: -1.4125

Max Act: 0.8915. Min Act: -0.0001

Data Index: 965388 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 1.4125. Min Range: -1.4125

Max Act: 0.9086. Min Act: -0.0001

Data Index: 393999 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 1.4125. Min Range: -1.4125

Max Act: 0.9479. Min Act: -0.0001

Data Index: 1239196 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 1.4125. Min Range: -1.4125

Max Act: 1.0017. Min Act: -0.0001

Data Index: 675282 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 1.4125. Min Range: -1.4125

Max Act: 0.8248. Min Act: -0.0001

Data Index: 348917 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 1.4125. Min Range: -1.4125

Max Act: 0.9221. Min Act: -0.0001

Data Index: 865602 (C4 (Web Text))

Max Activating Token Index: 688