Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 513 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3925. Min Act: -0.0001

Data Index: 92643 (C4 (Web Text))

Max Activating Token Index: 759

Text #1

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3488. Min Act: -0.0001

Data Index: 1293185 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3480. Min Act: -0.0001

Data Index: 179859 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3622. Min Act: -0.0001

Data Index: 63570 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3368. Min Act: -0.0001

Data Index: 1319727 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3337. Min Act: -0.0001

Data Index: 1303787 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3423. Min Act: -0.0001

Data Index: 403649 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3292. Min Act: -0.0001

Data Index: 1170823 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3317. Min Act: -0.0001

Data Index: 470696 (C4 (Web Text))

Max Activating Token Index: 1011

Text #9

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3331. Min Act: -0.0001

Data Index: 1344837 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3142. Min Act: -0.0001

Data Index: 718294 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3223. Min Act: -0.0001

Data Index: 490418 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3343. Min Act: -0.0001

Data Index: 1307563 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3108. Min Act: -0.0001

Data Index: 947665 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3308. Min Act: -0.0001

Data Index: 1145901 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3081. Min Act: -0.0001

Data Index: 41251 (C4 (Web Text))

Max Activating Token Index: 357

Text #16

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3140. Min Act: -0.0001

Data Index: 644448 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3290. Min Act: -0.0001

Data Index: 1102886 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3157. Min Act: -0.0001

Data Index: 1358693 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3049. Min Act: -0.0001

Data Index: 1244775 (C4 (Web Text))

Max Activating Token Index: 73