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

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

Neuron 1007 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: 0.3668. Min Range: -0.3668

Max Act: 0.3668. Min Act: -0.0001

Data Index: 9381 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.3386. Min Act: -0.0001

Data Index: 884218 (C4 (Web Text))

Max Activating Token Index: 447

Text #2

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.3350. Min Act: -0.0001

Data Index: 1201677 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.3225. Min Act: -0.0000

Data Index: 286110 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.3162. Min Act: -0.0001

Data Index: 912238 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2950. Min Act: -0.0001

Data Index: 93498 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2836. Min Act: -0.0001

Data Index: 301933 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2537. Min Act: -0.0001

Data Index: 1335510 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2713. Min Act: -0.0001

Data Index: 994889 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2704. Min Act: -0.0000

Data Index: 684492 (C4 (Web Text))

Max Activating Token Index: 663

Text #10

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2572. Min Act: -0.0001

Data Index: 11983 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2458. Min Act: -0.0001

Data Index: 1112944 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2681. Min Act: -0.0001

Data Index: 355678 (C4 (Web Text))

Max Activating Token Index: 550

Text #13

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2531. Min Act: -0.0001

Data Index: 1091313 (C4 (Web Text))

Max Activating Token Index: 126

Text #14

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2345. Min Act: -0.0001

Data Index: 585378 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2481. Min Act: -0.0001

Data Index: 879242 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2384. Min Act: -0.0001

Data Index: 610724 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2480. Min Act: -0.0000

Data Index: 1033397 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2426. Min Act: -0.0001

Data Index: 472090 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2277. Min Act: -0.0001

Data Index: 73942 (C4 (Web Text))

Max Activating Token Index: 889