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

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

Neuron 1511 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: 0.5143. Min Range: -0.5143

Max Act: 0.5143. Min Act: -0.0000

Data Index: 682055 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 0.5143. Min Range: -0.5143

Max Act: 0.4939. Min Act: -0.0000

Data Index: 485983 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 0.5143. Min Range: -0.5143

Max Act: 0.4522. Min Act: -0.0000

Data Index: 37673 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 0.5143. Min Range: -0.5143

Max Act: 0.4728. Min Act: -0.0000

Data Index: 487764 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 0.5143. Min Range: -0.5143

Max Act: 0.4686. Min Act: -0.0000

Data Index: 228774 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 0.5143. Min Range: -0.5143

Max Act: 0.4672. Min Act: -0.0000

Data Index: 1175275 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 0.5143. Min Range: -0.5143

Max Act: 0.4449. Min Act: -0.0000

Data Index: 1309270 (C4 (Web Text))

Max Activating Token Index: 993

Text #7

Max Range: 0.5143. Min Range: -0.5143

Max Act: 0.4586. Min Act: -0.0000

Data Index: 74089 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 0.5143. Min Range: -0.5143

Max Act: 0.4398. Min Act: -0.0000

Data Index: 92826 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 0.5143. Min Range: -0.5143

Max Act: 0.4522. Min Act: -0.0000

Data Index: 676927 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 0.5143. Min Range: -0.5143

Max Act: 0.4791. Min Act: -0.0000

Data Index: 1210508 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 0.5143. Min Range: -0.5143

Max Act: 0.4247. Min Act: -0.0000

Data Index: 919036 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 0.5143. Min Range: -0.5143

Max Act: 0.4388. Min Act: -0.0000

Data Index: 184676 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 0.5143. Min Range: -0.5143

Max Act: 0.4515. Min Act: -0.0000

Data Index: 94446 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 0.5143. Min Range: -0.5143

Max Act: 0.4336. Min Act: -0.0000

Data Index: 1077374 (C4 (Web Text))

Max Activating Token Index: 481

Text #15

Max Range: 0.5143. Min Range: -0.5143

Max Act: 0.4325. Min Act: -0.0000

Data Index: 403085 (C4 (Web Text))

Max Activating Token Index: 560

Text #16

Max Range: 0.5143. Min Range: -0.5143

Max Act: 0.4421. Min Act: -0.0000

Data Index: 693999 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 0.5143. Min Range: -0.5143

Max Act: 0.4419. Min Act: -0.0000

Data Index: 741143 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 0.5143. Min Range: -0.5143

Max Act: 0.4108. Min Act: -0.0000

Data Index: 484182 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 0.5143. Min Range: -0.5143

Max Act: 0.4213. Min Act: -0.0000

Data Index: 666106 (C4 (Web Text))

Max Activating Token Index: 495