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

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

Neuron 385 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.3177. Min Act: -0.0000

Data Index: 930458 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.3078. Min Act: -0.0000

Data Index: 1341533 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2898. Min Act: -0.0001

Data Index: 1159833 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2786. Min Act: -0.0000

Data Index: 1205778 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2759. Min Act: -0.0000

Data Index: 1270035 (C4 (Web Text))

Max Activating Token Index: 448

Text #5

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2751. Min Act: -0.0001

Data Index: 129832 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2804. Min Act: -0.0000

Data Index: 170849 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2566. Min Act: -0.0000

Data Index: 947492 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2588. Min Act: -0.0000

Data Index: 869565 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2567. Min Act: -0.0001

Data Index: 927515 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2578. Min Act: -0.0000

Data Index: 631678 (C4 (Web Text))

Max Activating Token Index: 292

Text #11

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2380. Min Act: -0.0001

Data Index: 966505 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2391. Min Act: -0.0001

Data Index: 1223285 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2253. Min Act: -0.0000

Data Index: 1035983 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2316. Min Act: -0.0000

Data Index: 101453 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2077. Min Act: -0.0000

Data Index: 276754 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2301. Min Act: -0.0000

Data Index: 61932 (C4 (Web Text))

Max Activating Token Index: 274

Text #17

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2182. Min Act: -0.0000

Data Index: 821375 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2141. Min Act: -0.0000

Data Index: 106030 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2351. Min Act: -0.0000

Data Index: 1251047 (C4 (Web Text))

Max Activating Token Index: 287