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

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

Neuron 3696 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1069. Min Range: -1.1069

Max Act: 1.1069. Min Act: -0.0000

Data Index: 186164 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 1.1069. Min Range: -1.1069

Max Act: 1.0263. Min Act: -0.0000

Data Index: 1302950 (C4 (Web Text))

Max Activating Token Index: 802

Text #2

Max Range: 1.1069. Min Range: -1.1069

Max Act: 0.9179. Min Act: -0.0000

Data Index: 797217 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 1.1069. Min Range: -1.1069

Max Act: 0.8704. Min Act: -0.0000

Data Index: 196993 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 1.1069. Min Range: -1.1069

Max Act: 0.7704. Min Act: -0.0000

Data Index: 952328 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 1.1069. Min Range: -1.1069

Max Act: 0.8130. Min Act: -0.0000

Data Index: 973498 (C4 (Web Text))

Max Activating Token Index: 927

Text #6

Max Range: 1.1069. Min Range: -1.1069

Max Act: 0.7814. Min Act: -0.0000

Data Index: 1011238 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 1.1069. Min Range: -1.1069

Max Act: 0.7307. Min Act: -0.0000

Data Index: 508284 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 1.1069. Min Range: -1.1069

Max Act: 0.6373. Min Act: -0.0000

Data Index: 627088 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 1.1069. Min Range: -1.1069

Max Act: 0.7161. Min Act: -0.0000

Data Index: 438578 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 1.1069. Min Range: -1.1069

Max Act: 0.6617. Min Act: -0.0000

Data Index: 780222 (C4 (Web Text))

Max Activating Token Index: 1013

Text #11

Max Range: 1.1069. Min Range: -1.1069

Max Act: 0.6414. Min Act: -0.0000

Data Index: 604311 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 1.1069. Min Range: -1.1069

Max Act: 0.6273. Min Act: -0.0000

Data Index: 183030 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 1.1069. Min Range: -1.1069

Max Act: 0.6298. Min Act: -0.0000

Data Index: 451850 (C4 (Web Text))

Max Activating Token Index: 711

Text #14

Max Range: 1.1069. Min Range: -1.1069

Max Act: 0.6244. Min Act: -0.0000

Data Index: 919522 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 1.1069. Min Range: -1.1069

Max Act: 0.6178. Min Act: -0.0000

Data Index: 375904 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 1.1069. Min Range: -1.1069

Max Act: 0.6205. Min Act: -0.0000

Data Index: 319208 (C4 (Web Text))

Max Activating Token Index: 501

Text #17

Max Range: 1.1069. Min Range: -1.1069

Max Act: 0.6083. Min Act: -0.0000

Data Index: 818433 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 1.1069. Min Range: -1.1069

Max Act: 0.6450. Min Act: -0.0000

Data Index: 590942 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 1.1069. Min Range: -1.1069

Max Act: 0.6060. Min Act: -0.0000

Data Index: 835249 (C4 (Web Text))

Max Activating Token Index: 788