Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1111 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.0363. Min Range: -2.0363

Max Act: 2.0363. Min Act: -0.0000

Data Index: 1254422 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 2.0363. Min Range: -2.0363

Max Act: 2.0183. Min Act: -0.0000

Data Index: 595504 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 2.0363. Min Range: -2.0363

Max Act: 1.6837. Min Act: -0.0000

Data Index: 296541 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 2.0363. Min Range: -2.0363

Max Act: 1.6422. Min Act: -0.0000

Data Index: 1245205 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 2.0363. Min Range: -2.0363

Max Act: 1.5397. Min Act: -0.0000

Data Index: 1269679 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 2.0363. Min Range: -2.0363

Max Act: 1.4976. Min Act: -0.0000

Data Index: 946444 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 2.0363. Min Range: -2.0363

Max Act: 1.4949. Min Act: -0.0000

Data Index: 862261 (C4 (Web Text))

Max Activating Token Index: 931

Text #7

Max Range: 2.0363. Min Range: -2.0363

Max Act: 1.4645. Min Act: -0.0000

Data Index: 1157971 (C4 (Web Text))

Max Activating Token Index: 387

Text #8

Max Range: 2.0363. Min Range: -2.0363

Max Act: 1.4503. Min Act: -0.0000

Data Index: 837943 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 2.0363. Min Range: -2.0363

Max Act: 1.5293. Min Act: -0.0000

Data Index: 493641 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 2.0363. Min Range: -2.0363

Max Act: 1.4253. Min Act: -0.0000

Data Index: 1225391 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 2.0363. Min Range: -2.0363

Max Act: 1.3295. Min Act: -0.0000

Data Index: 140959 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 2.0363. Min Range: -2.0363

Max Act: 1.3861. Min Act: -0.0000

Data Index: 402760 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 2.0363. Min Range: -2.0363

Max Act: 1.3859. Min Act: -0.0000

Data Index: 707026 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 2.0363. Min Range: -2.0363

Max Act: 1.4650. Min Act: -0.0000

Data Index: 487599 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 2.0363. Min Range: -2.0363

Max Act: 1.4277. Min Act: -0.0000

Data Index: 711566 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 2.0363. Min Range: -2.0363

Max Act: 1.2801. Min Act: -0.0000

Data Index: 511262 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 2.0363. Min Range: -2.0363

Max Act: 1.2740. Min Act: -0.0000

Data Index: 762646 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 2.0363. Min Range: -2.0363

Max Act: 1.3216. Min Act: -0.0000

Data Index: 808033 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 2.0363. Min Range: -2.0363

Max Act: 1.1450. Min Act: -0.0000

Data Index: 433979 (C4 (Web Text))

Max Activating Token Index: 764