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

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

Neuron 494 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.3092. Min Act: -0.0000

Data Index: 1353179 (C4 (Web Text))

Max Activating Token Index: 461

Text #1

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.1163. Min Act: -0.0000

Data Index: 430169 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.0510. Min Act: -0.0000

Data Index: 230480 (C4 (Web Text))

Max Activating Token Index: 625

Text #3

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.0556. Min Act: -0.0000

Data Index: 418753 (C4 (Web Text))

Max Activating Token Index: 436

Text #4

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.9564. Min Act: -0.0000

Data Index: 979476 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.9977. Min Act: -0.0000

Data Index: 1288056 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.0322. Min Act: -0.0000

Data Index: 1286963 (C4 (Web Text))

Max Activating Token Index: 668

Text #7

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.0175. Min Act: -0.0001

Data Index: 1290311 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.9626. Min Act: -0.0000

Data Index: 582950 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.9426. Min Act: -0.0000

Data Index: 1290979 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.0331. Min Act: -0.0000

Data Index: 123829 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.0002. Min Act: -0.0000

Data Index: 1178361 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.8912. Min Act: -0.0000

Data Index: 1001831 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.9419. Min Act: -0.0000

Data Index: 646909 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.8555. Min Act: -0.0000

Data Index: 856337 (C4 (Web Text))

Max Activating Token Index: 656

Text #15

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.9018. Min Act: -0.0001

Data Index: 1521646 (Python Code)

Max Activating Token Index: 661

Text #16

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.9036. Min Act: -0.0000

Data Index: 1190798 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.9273. Min Act: -0.0001

Data Index: 1629422 (Python Code)

Max Activating Token Index: 418

Text #18

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.8980. Min Act: -0.0000

Data Index: 906992 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.9179. Min Act: -0.0001

Data Index: 330772 (C4 (Web Text))

Max Activating Token Index: 712