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

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

Neuron 2191 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.4802. Min Act: -0.0000

Data Index: 572330 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.4659. Min Act: -0.0000

Data Index: 993610 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.4077. Min Act: -0.0000

Data Index: 807485 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3694. Min Act: -0.0001

Data Index: 699825 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3575. Min Act: -0.0000

Data Index: 1349100 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3458. Min Act: -0.0000

Data Index: 10798 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3357. Min Act: -0.0001

Data Index: 1068629 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3343. Min Act: -0.0000

Data Index: 864712 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3204. Min Act: -0.0000

Data Index: 444866 (C4 (Web Text))

Max Activating Token Index: 546

Text #9

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3183. Min Act: -0.0000

Data Index: 1152819 (C4 (Web Text))

Max Activating Token Index: 757

Text #10

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3269. Min Act: -0.0000

Data Index: 695080 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3252. Min Act: -0.0000

Data Index: 64997 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3238. Min Act: -0.0000

Data Index: 867298 (C4 (Web Text))

Max Activating Token Index: 553

Text #13

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3214. Min Act: -0.0001

Data Index: 1234436 (C4 (Web Text))

Max Activating Token Index: 632

Text #14

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3327. Min Act: -0.0001

Data Index: 281856 (C4 (Web Text))

Max Activating Token Index: 515

Text #15

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3130. Min Act: -0.0000

Data Index: 115065 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3037. Min Act: -0.0001

Data Index: 399903 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3018. Min Act: -0.0001

Data Index: 1334291 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3129. Min Act: -0.0001

Data Index: 89036 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3106. Min Act: -0.0001

Data Index: 1008153 (C4 (Web Text))

Max Activating Token Index: 763