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

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

Neuron 815 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4242. Min Range: -0.4242

Max Act: 0.4242. Min Act: -0.0001

Data Index: 1179766 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 0.4242. Min Range: -0.4242

Max Act: 0.4125. Min Act: -0.0001

Data Index: 718185 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 0.4242. Min Range: -0.4242

Max Act: 0.3967. Min Act: -0.0001

Data Index: 850091 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 0.4242. Min Range: -0.4242

Max Act: 0.3889. Min Act: -0.0001

Data Index: 1086101 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 0.4242. Min Range: -0.4242

Max Act: 0.3841. Min Act: -0.0001

Data Index: 839937 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 0.4242. Min Range: -0.4242

Max Act: 0.3368. Min Act: -0.0001

Data Index: 1156549 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 0.4242. Min Range: -0.4242

Max Act: 0.3600. Min Act: -0.0001

Data Index: 926569 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 0.4242. Min Range: -0.4242

Max Act: 0.3358. Min Act: -0.0001

Data Index: 841681 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 0.4242. Min Range: -0.4242

Max Act: 0.3365. Min Act: -0.0001

Data Index: 362749 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 0.4242. Min Range: -0.4242

Max Act: 0.3380. Min Act: -0.0001

Data Index: 139964 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 0.4242. Min Range: -0.4242

Max Act: 0.3235. Min Act: -0.0001

Data Index: 458470 (C4 (Web Text))

Max Activating Token Index: 712

Text #11

Max Range: 0.4242. Min Range: -0.4242

Max Act: 0.3191. Min Act: -0.0001

Data Index: 835024 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 0.4242. Min Range: -0.4242

Max Act: 0.3134. Min Act: -0.0001

Data Index: 741449 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 0.4242. Min Range: -0.4242

Max Act: 0.3207. Min Act: -0.0001

Data Index: 1276439 (C4 (Web Text))

Max Activating Token Index: 521

Text #14

Max Range: 0.4242. Min Range: -0.4242

Max Act: 0.3272. Min Act: -0.0001

Data Index: 645950 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 0.4242. Min Range: -0.4242

Max Act: 0.3267. Min Act: -0.0001

Data Index: 1206278 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 0.4242. Min Range: -0.4242

Max Act: 0.3118. Min Act: -0.0001

Data Index: 942644 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 0.4242. Min Range: -0.4242

Max Act: 0.3221. Min Act: -0.0001

Data Index: 1079840 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 0.4242. Min Range: -0.4242

Max Act: 0.3309. Min Act: -0.0001

Data Index: 983064 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 0.4242. Min Range: -0.4242

Max Act: 0.3215. Min Act: -0.0001

Data Index: 1286556 (C4 (Web Text))

Max Activating Token Index: 619