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

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

Neuron 1808 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4942. Min Act: -0.0000

Data Index: 112936 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4831. Min Act: -0.0000

Data Index: 421382 (C4 (Web Text))

Max Activating Token Index: 297

Text #2

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.3797. Min Act: -0.0000

Data Index: 720929 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4445. Min Act: -0.0000

Data Index: 225881 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.3912. Min Act: -0.0000

Data Index: 899985 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4363. Min Act: -0.0000

Data Index: 316032 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.3652. Min Act: -0.0000

Data Index: 1308967 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.3638. Min Act: -0.0000

Data Index: 92717 (C4 (Web Text))

Max Activating Token Index: 531

Text #8

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.3477. Min Act: -0.0000

Data Index: 455982 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.3433. Min Act: -0.0000

Data Index: 1073293 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.3369. Min Act: -0.0000

Data Index: 690908 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.3265. Min Act: -0.0000

Data Index: 746034 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.3454. Min Act: -0.0000

Data Index: 68624 (C4 (Web Text))

Max Activating Token Index: 382

Text #13

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.3293. Min Act: -0.0000

Data Index: 608402 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.3225. Min Act: -0.0000

Data Index: 1336878 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.3467. Min Act: -0.0000

Data Index: 723930 (C4 (Web Text))

Max Activating Token Index: 927

Text #16

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.3187. Min Act: -0.0000

Data Index: 1180166 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.3277. Min Act: -0.0000

Data Index: 1206180 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.3095. Min Act: -0.0000

Data Index: 1001392 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.3117. Min Act: -0.0000

Data Index: 924283 (C4 (Web Text))

Max Activating Token Index: 358