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

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

Neuron 2795 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7572. Min Range: -0.7572

Max Act: 0.7572. Min Act: -0.0000

Data Index: 791386 (C4 (Web Text))

Max Activating Token Index: 293

Text #1

Max Range: 0.7572. Min Range: -0.7572

Max Act: 0.7263. Min Act: -0.0000

Data Index: 726905 (C4 (Web Text))

Max Activating Token Index: 205

Text #2

Max Range: 0.7572. Min Range: -0.7572

Max Act: 0.6443. Min Act: -0.0000

Data Index: 14950 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 0.7572. Min Range: -0.7572

Max Act: 0.6582. Min Act: -0.0000

Data Index: 1199838 (C4 (Web Text))

Max Activating Token Index: 649

Text #4

Max Range: 0.7572. Min Range: -0.7572

Max Act: 0.6458. Min Act: -0.0000

Data Index: 532669 (C4 (Web Text))

Max Activating Token Index: 663

Text #5

Max Range: 0.7572. Min Range: -0.7572

Max Act: 0.6235. Min Act: -0.0000

Data Index: 1292639 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 0.7572. Min Range: -0.7572

Max Act: 0.6200. Min Act: -0.0000

Data Index: 1725 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 0.7572. Min Range: -0.7572

Max Act: 0.6020. Min Act: -0.0000

Data Index: 668798 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 0.7572. Min Range: -0.7572

Max Act: 0.5584. Min Act: -0.0000

Data Index: 856554 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 0.7572. Min Range: -0.7572

Max Act: 0.5315. Min Act: -0.0000

Data Index: 408169 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 0.7572. Min Range: -0.7572

Max Act: 0.5688. Min Act: -0.0000

Data Index: 1278103 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 0.7572. Min Range: -0.7572

Max Act: 0.5538. Min Act: -0.0000

Data Index: 500679 (C4 (Web Text))

Max Activating Token Index: 470

Text #12

Max Range: 0.7572. Min Range: -0.7572

Max Act: 0.5312. Min Act: -0.0000

Data Index: 132338 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 0.7572. Min Range: -0.7572

Max Act: 0.5415. Min Act: -0.0000

Data Index: 1330965 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 0.7572. Min Range: -0.7572

Max Act: 0.5545. Min Act: -0.0000

Data Index: 139425 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 0.7572. Min Range: -0.7572

Max Act: 0.5405. Min Act: -0.0000

Data Index: 1156311 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 0.7572. Min Range: -0.7572

Max Act: 0.5679. Min Act: -0.0000

Data Index: 113180 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 0.7572. Min Range: -0.7572

Max Act: 0.5372. Min Act: -0.0000

Data Index: 195745 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 0.7572. Min Range: -0.7572

Max Act: 0.5366. Min Act: -0.0000

Data Index: 797051 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 0.7572. Min Range: -0.7572

Max Act: 0.5595. Min Act: -0.0000

Data Index: 1163538 (C4 (Web Text))

Max Activating Token Index: 47