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

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

Neuron 4042 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9404. Min Range: -1.9404

Max Act: 1.9404. Min Act: -0.0001

Data Index: 105229 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 1.9404. Min Range: -1.9404

Max Act: 1.6990. Min Act: -0.0001

Data Index: 950793 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 1.9404. Min Range: -1.9404

Max Act: 1.6892. Min Act: -0.0001

Data Index: 523282 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 1.9404. Min Range: -1.9404

Max Act: 1.7657. Min Act: -0.0001

Data Index: 553065 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 1.9404. Min Range: -1.9404

Max Act: 1.7174. Min Act: -0.0001

Data Index: 833108 (C4 (Web Text))

Max Activating Token Index: 394

Text #5

Max Range: 1.9404. Min Range: -1.9404

Max Act: 1.5990. Min Act: -0.0001

Data Index: 145798 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 1.9404. Min Range: -1.9404

Max Act: 1.6347. Min Act: -0.0001

Data Index: 714693 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 1.9404. Min Range: -1.9404

Max Act: 1.6423. Min Act: -0.0001

Data Index: 1113547 (C4 (Web Text))

Max Activating Token Index: 605

Text #8

Max Range: 1.9404. Min Range: -1.9404

Max Act: 1.4865. Min Act: -0.0001

Data Index: 258443 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 1.9404. Min Range: -1.9404

Max Act: 1.5352. Min Act: -0.0001

Data Index: 401649 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 1.9404. Min Range: -1.9404

Max Act: 1.4645. Min Act: -0.0001

Data Index: 1207767 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 1.9404. Min Range: -1.9404

Max Act: 1.4241. Min Act: -0.0001

Data Index: 603080 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 1.9404. Min Range: -1.9404

Max Act: 1.5402. Min Act: -0.0001

Data Index: 499754 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 1.9404. Min Range: -1.9404

Max Act: 1.4061. Min Act: -0.0001

Data Index: 986551 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 1.9404. Min Range: -1.9404

Max Act: 1.4840. Min Act: -0.0001

Data Index: 5925 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 1.9404. Min Range: -1.9404

Max Act: 1.6277. Min Act: -0.0001

Data Index: 648279 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 1.9404. Min Range: -1.9404

Max Act: 1.2865. Min Act: -0.0001

Data Index: 548038 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 1.9404. Min Range: -1.9404

Max Act: 1.4225. Min Act: -0.0001

Data Index: 204200 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 1.9404. Min Range: -1.9404

Max Act: 1.4248. Min Act: -0.0001

Data Index: 1199318 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 1.9404. Min Range: -1.9404

Max Act: 1.3836. Min Act: -0.0001

Data Index: 1227421 (C4 (Web Text))

Max Activating Token Index: 458