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

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

Neuron 3290 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: 1.3196. Min Range: -1.3196

Max Act: 1.3196. Min Act: -0.0000

Data Index: 483128 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 1.3196. Min Range: -1.3196

Max Act: 1.2249. Min Act: -0.0000

Data Index: 222793 (C4 (Web Text))

Max Activating Token Index: 802

Text #2

Max Range: 1.3196. Min Range: -1.3196

Max Act: 1.1352. Min Act: -0.0000

Data Index: 410153 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 1.3196. Min Range: -1.3196

Max Act: 1.1296. Min Act: -0.0000

Data Index: 63430 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 1.3196. Min Range: -1.3196

Max Act: 1.0072. Min Act: -0.0000

Data Index: 149070 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 1.3196. Min Range: -1.3196

Max Act: 0.9741. Min Act: -0.0000

Data Index: 917965 (C4 (Web Text))

Max Activating Token Index: 538

Text #6

Max Range: 1.3196. Min Range: -1.3196

Max Act: 0.9646. Min Act: -0.0000

Data Index: 876445 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 1.3196. Min Range: -1.3196

Max Act: 0.9997. Min Act: -0.0000

Data Index: 1050192 (C4 (Web Text))

Max Activating Token Index: 366

Text #8

Max Range: 1.3196. Min Range: -1.3196

Max Act: 0.9217. Min Act: -0.0000

Data Index: 1035030 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 1.3196. Min Range: -1.3196

Max Act: 0.9577. Min Act: -0.0000

Data Index: 1234992 (C4 (Web Text))

Max Activating Token Index: 403

Text #10

Max Range: 1.3196. Min Range: -1.3196

Max Act: 0.9459. Min Act: -0.0000

Data Index: 678221 (C4 (Web Text))

Max Activating Token Index: 925

Text #11

Max Range: 1.3196. Min Range: -1.3196

Max Act: 0.9330. Min Act: -0.0000

Data Index: 325545 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 1.3196. Min Range: -1.3196

Max Act: 0.8691. Min Act: -0.0000

Data Index: 610557 (C4 (Web Text))

Max Activating Token Index: 358

Text #13

Max Range: 1.3196. Min Range: -1.3196

Max Act: 0.9267. Min Act: -0.0000

Data Index: 875192 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 1.3196. Min Range: -1.3196

Max Act: 0.9143. Min Act: -0.0000

Data Index: 114556 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 1.3196. Min Range: -1.3196

Max Act: 0.9171. Min Act: -0.0000

Data Index: 358653 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 1.3196. Min Range: -1.3196

Max Act: 0.9048. Min Act: -0.0000

Data Index: 473564 (C4 (Web Text))

Max Activating Token Index: 578

Text #17

Max Range: 1.3196. Min Range: -1.3196

Max Act: 0.9032. Min Act: -0.0000

Data Index: 1224458 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 1.3196. Min Range: -1.3196

Max Act: 0.8997. Min Act: -0.0000

Data Index: 1292629 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 1.3196. Min Range: -1.3196

Max Act: 0.8920. Min Act: -0.0000

Data Index: 396283 (C4 (Web Text))

Max Activating Token Index: 782