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

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

Neuron 2803 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: 0.4299. Min Range: -0.4299

Max Act: 0.4244. Min Act: -0.0001

Data Index: 86649 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 0.4299. Min Range: -0.4299

Max Act: 0.4299. Min Act: -0.0001

Data Index: 661744 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 0.4299. Min Range: -0.4299

Max Act: 0.3900. Min Act: -0.0001

Data Index: 816504 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 0.4299. Min Range: -0.4299

Max Act: 0.2623. Min Act: -0.0001

Data Index: 1280072 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 0.4299. Min Range: -0.4299

Max Act: 0.2785. Min Act: -0.0000

Data Index: 713539 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 0.4299. Min Range: -0.4299

Max Act: 0.3004. Min Act: -0.0001

Data Index: 762355 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 0.4299. Min Range: -0.4299

Max Act: 0.2777. Min Act: -0.0000

Data Index: 848167 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 0.4299. Min Range: -0.4299

Max Act: 0.2690. Min Act: -0.0000

Data Index: 485301 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 0.4299. Min Range: -0.4299

Max Act: 0.2666. Min Act: -0.0001

Data Index: 201414 (C4 (Web Text))

Max Activating Token Index: 838

Text #9

Max Range: 0.4299. Min Range: -0.4299

Max Act: 0.2739. Min Act: -0.0001

Data Index: 578304 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 0.4299. Min Range: -0.4299

Max Act: 0.2665. Min Act: -0.0001

Data Index: 506190 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 0.4299. Min Range: -0.4299

Max Act: 0.2776. Min Act: -0.0001

Data Index: 1351114 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 0.4299. Min Range: -0.4299

Max Act: 0.2732. Min Act: -0.0000

Data Index: 374532 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 0.4299. Min Range: -0.4299

Max Act: 0.2616. Min Act: -0.0001

Data Index: 660977 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 0.4299. Min Range: -0.4299

Max Act: 0.2551. Min Act: -0.0001

Data Index: 1042268 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 0.4299. Min Range: -0.4299

Max Act: 0.2449. Min Act: -0.0000

Data Index: 1009396 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 0.4299. Min Range: -0.4299

Max Act: 0.2274. Min Act: -0.0000

Data Index: 597240 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 0.4299. Min Range: -0.4299

Max Act: 0.2443. Min Act: -0.0001

Data Index: 94459 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 0.4299. Min Range: -0.4299

Max Act: 0.2220. Min Act: -0.0001

Data Index: 482696 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 0.4299. Min Range: -0.4299

Max Act: 0.2303. Min Act: -0.0001

Data Index: 943572 (C4 (Web Text))

Max Activating Token Index: 341