Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1324 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0431. Min Act: -0.0006

Data Index: 1233283 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0351. Min Act: -0.0006

Data Index: 178539 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0334. Min Act: -0.0006

Data Index: 231108 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0346. Min Act: -0.0006

Data Index: 518127 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0339. Min Act: -0.0006

Data Index: 663342 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0336. Min Act: -0.0006

Data Index: 1355675 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0318. Min Act: -0.0006

Data Index: 96010 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0325. Min Act: -0.0006

Data Index: 994677 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0312. Min Act: -0.0006

Data Index: 457674 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0314. Min Act: -0.0006

Data Index: 127375 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0319. Min Act: -0.0006

Data Index: 532446 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0303. Min Act: -0.0006

Data Index: 1065567 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0306. Min Act: -0.0006

Data Index: 936875 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0300. Min Act: -0.0006

Data Index: 441804 (C4 (Web Text))

Max Activating Token Index: 304

Text #14

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0296. Min Act: -0.0006

Data Index: 384922 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0298. Min Act: -0.0006

Data Index: 5892 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0297. Min Act: -0.0006

Data Index: 407234 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0296. Min Act: -0.0006

Data Index: 1118673 (C4 (Web Text))

Max Activating Token Index: 965

Text #18

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0286. Min Act: -0.0006

Data Index: 49131 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0298. Min Act: -0.0006

Data Index: 345766 (C4 (Web Text))

Max Activating Token Index: 807