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

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

Neuron 2570 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.5338. Min Act: -0.0001

Data Index: 981000 (C4 (Web Text))

Max Activating Token Index: 977

Text #1

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.5304. Min Act: -0.0001

Data Index: 1078908 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.3776. Min Act: -0.0001

Data Index: 763329 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.3440. Min Act: -0.0001

Data Index: 437106 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.3987. Min Act: -0.0001

Data Index: 511544 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.2882. Min Act: -0.0001

Data Index: 1119839 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.2969. Min Act: -0.0001

Data Index: 251053 (C4 (Web Text))

Max Activating Token Index: 645

Text #7

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.4106. Min Act: -0.0001

Data Index: 848881 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.3510. Min Act: -0.0001

Data Index: 334038 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.3198. Min Act: -0.0001

Data Index: 898325 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.2871. Min Act: -0.0001

Data Index: 638580 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.3571. Min Act: -0.0001

Data Index: 200502 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.1905. Min Act: -0.0001

Data Index: 49437 (C4 (Web Text))

Max Activating Token Index: 754

Text #13

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.2260. Min Act: -0.0001

Data Index: 599657 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.2277. Min Act: -0.0001

Data Index: 23809 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.1467. Min Act: -0.0001

Data Index: 767894 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.2818. Min Act: -0.0001

Data Index: 365265 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.3913. Min Act: -0.0001

Data Index: 445618 (C4 (Web Text))

Max Activating Token Index: 960

Text #18

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.2213. Min Act: -0.0001

Data Index: 240380 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.2174. Min Act: -0.0001

Data Index: 999378 (C4 (Web Text))

Max Activating Token Index: 27