Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3276 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.5152. Min Act: -0.0000

Data Index: 493823 (C4 (Web Text))

Max Activating Token Index: 974

Text #1

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4371. Min Act: -0.0000

Data Index: 118578 (C4 (Web Text))

Max Activating Token Index: 448

Text #2

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4037. Min Act: -0.0000

Data Index: 1106848 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4384. Min Act: -0.0001

Data Index: 594264 (C4 (Web Text))

Max Activating Token Index: 505

Text #4

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4423. Min Act: -0.0001

Data Index: 1294457 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4080. Min Act: -0.0000

Data Index: 403222 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.4021. Min Act: -0.0000

Data Index: 177315 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.3663. Min Act: -0.0000

Data Index: 152479 (C4 (Web Text))

Max Activating Token Index: 285

Text #8

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.3718. Min Act: -0.0001

Data Index: 1011677 (C4 (Web Text))

Max Activating Token Index: 699

Text #9

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.3301. Min Act: -0.0000

Data Index: 32407 (C4 (Web Text))

Max Activating Token Index: 845

Text #10

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.3253. Min Act: -0.0001

Data Index: 1307490 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.3362. Min Act: -0.0000

Data Index: 690161 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.3411. Min Act: -0.0000

Data Index: 138523 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.3469. Min Act: -0.0000

Data Index: 984318 (C4 (Web Text))

Max Activating Token Index: 674

Text #14

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.3317. Min Act: -0.0001

Data Index: 830464 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.3177. Min Act: -0.0000

Data Index: 834315 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.2944. Min Act: -0.0000

Data Index: 96823 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.3131. Min Act: -0.0000

Data Index: 1155531 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.3162. Min Act: -0.0000

Data Index: 104123 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 0.5152. Min Range: -0.5152

Max Act: 0.3013. Min Act: -0.0000

Data Index: 602724 (C4 (Web Text))

Max Activating Token Index: 985