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

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

Neuron 4827 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: 3.2515. Min Range: -3.2515

Max Act: 3.2515. Min Act: -0.0000

Data Index: 1164973 (C4 (Web Text))

Max Activating Token Index: 383

Text #1

Max Range: 3.2515. Min Range: -3.2515

Max Act: 2.6796. Min Act: -0.0000

Data Index: 1138597 (C4 (Web Text))

Max Activating Token Index: 933

Text #2

Max Range: 3.2515. Min Range: -3.2515

Max Act: 2.5957. Min Act: -0.0000

Data Index: 316757 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 3.2515. Min Range: -3.2515

Max Act: 2.7042. Min Act: -0.0000

Data Index: 478346 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 3.2515. Min Range: -3.2515

Max Act: 2.5614. Min Act: -0.0000

Data Index: 237478 (C4 (Web Text))

Max Activating Token Index: 928

Text #5

Max Range: 3.2515. Min Range: -3.2515

Max Act: 2.3244. Min Act: -0.0000

Data Index: 652151 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 3.2515. Min Range: -3.2515

Max Act: 2.4083. Min Act: -0.0000

Data Index: 659359 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 3.2515. Min Range: -3.2515

Max Act: 2.4181. Min Act: -0.0000

Data Index: 208755 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 3.2515. Min Range: -3.2515

Max Act: 2.4060. Min Act: -0.0000

Data Index: 346412 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 3.2515. Min Range: -3.2515

Max Act: 2.4562. Min Act: -0.0000

Data Index: 1222311 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 3.2515. Min Range: -3.2515

Max Act: 2.3031. Min Act: -0.0000

Data Index: 1044270 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 3.2515. Min Range: -3.2515

Max Act: 2.2682. Min Act: -0.0000

Data Index: 456342 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 3.2515. Min Range: -3.2515

Max Act: 2.3312. Min Act: -0.0000

Data Index: 413843 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 3.2515. Min Range: -3.2515

Max Act: 2.0989. Min Act: -0.0000

Data Index: 662459 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 3.2515. Min Range: -3.2515

Max Act: 2.3170. Min Act: -0.0000

Data Index: 104356 (C4 (Web Text))

Max Activating Token Index: 858

Text #15

Max Range: 3.2515. Min Range: -3.2515

Max Act: 2.1993. Min Act: -0.0000

Data Index: 105852 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 3.2515. Min Range: -3.2515

Max Act: 2.1794. Min Act: -0.0000

Data Index: 1138802 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 3.2515. Min Range: -3.2515

Max Act: 2.0512. Min Act: -0.0000

Data Index: 452624 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 3.2515. Min Range: -3.2515

Max Act: 2.1505. Min Act: -0.0000

Data Index: 339989 (C4 (Web Text))

Max Activating Token Index: 93

Text #19

Max Range: 3.2515. Min Range: -3.2515

Max Act: 2.1329. Min Act: -0.0000

Data Index: 1125855 (C4 (Web Text))

Max Activating Token Index: 981