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

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

Neuron 4621 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.4949. Min Range: -0.4949

Max Act: 0.4949. Min Act: -0.0001

Data Index: 901004 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 0.4949. Min Range: -0.4949

Max Act: 0.3822. Min Act: -0.0001

Data Index: 908312 (C4 (Web Text))

Max Activating Token Index: 439

Text #2

Max Range: 0.4949. Min Range: -0.4949

Max Act: 0.3587. Min Act: -0.0001

Data Index: 478658 (C4 (Web Text))

Max Activating Token Index: 485

Text #3

Max Range: 0.4949. Min Range: -0.4949

Max Act: 0.3689. Min Act: -0.0001

Data Index: 305220 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 0.4949. Min Range: -0.4949

Max Act: 0.3576. Min Act: -0.0001

Data Index: 769346 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 0.4949. Min Range: -0.4949

Max Act: 0.3478. Min Act: -0.0001

Data Index: 1094693 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 0.4949. Min Range: -0.4949

Max Act: 0.3439. Min Act: -0.0001

Data Index: 349783 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 0.4949. Min Range: -0.4949

Max Act: 0.3518. Min Act: -0.0001

Data Index: 821419 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 0.4949. Min Range: -0.4949

Max Act: 0.3569. Min Act: -0.0001

Data Index: 182361 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 0.4949. Min Range: -0.4949

Max Act: 0.3409. Min Act: -0.0001

Data Index: 1165474 (C4 (Web Text))

Max Activating Token Index: 405

Text #10

Max Range: 0.4949. Min Range: -0.4949

Max Act: 0.3312. Min Act: -0.0001

Data Index: 289980 (C4 (Web Text))

Max Activating Token Index: 244

Text #11

Max Range: 0.4949. Min Range: -0.4949

Max Act: 0.3322. Min Act: -0.0001

Data Index: 1178442 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 0.4949. Min Range: -0.4949

Max Act: 0.3320. Min Act: -0.0001

Data Index: 33090 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 0.4949. Min Range: -0.4949

Max Act: 0.3315. Min Act: -0.0001

Data Index: 172657 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 0.4949. Min Range: -0.4949

Max Act: 0.3355. Min Act: -0.0001

Data Index: 298104 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 0.4949. Min Range: -0.4949

Max Act: 0.3290. Min Act: -0.0001

Data Index: 1059561 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 0.4949. Min Range: -0.4949

Max Act: 0.3336. Min Act: -0.0001

Data Index: 261813 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 0.4949. Min Range: -0.4949

Max Act: 0.3239. Min Act: -0.0001

Data Index: 566292 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 0.4949. Min Range: -0.4949

Max Act: 0.3260. Min Act: -0.0001

Data Index: 494729 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 0.4949. Min Range: -0.4949

Max Act: 0.3319. Min Act: -0.0001

Data Index: 854442 (C4 (Web Text))

Max Activating Token Index: 276