Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 551 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5964. Min Range: -1.5964

Max Act: 1.5964. Min Act: -0.0000

Data Index: 256015 (C4 (Web Text))

Max Activating Token Index: 759

Text #1

Max Range: 1.5964. Min Range: -1.5964

Max Act: 1.2893. Min Act: -0.0000

Data Index: 364832 (C4 (Web Text))

Max Activating Token Index: 652

Text #2

Max Range: 1.5964. Min Range: -1.5964

Max Act: 1.4302. Min Act: -0.0000

Data Index: 727076 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 1.5964. Min Range: -1.5964

Max Act: 1.3147. Min Act: -0.0000

Data Index: 247855 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 1.5964. Min Range: -1.5964

Max Act: 1.2163. Min Act: -0.0000

Data Index: 371336 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 1.5964. Min Range: -1.5964

Max Act: 1.3322. Min Act: -0.0000

Data Index: 1115181 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 1.5964. Min Range: -1.5964

Max Act: 1.2197. Min Act: -0.0000

Data Index: 752849 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 1.5964. Min Range: -1.5964

Max Act: 1.1248. Min Act: -0.0000

Data Index: 1285781 (C4 (Web Text))

Max Activating Token Index: 427

Text #8

Max Range: 1.5964. Min Range: -1.5964

Max Act: 1.1235. Min Act: -0.0000

Data Index: 571229 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 1.5964. Min Range: -1.5964

Max Act: 1.1115. Min Act: -0.0000

Data Index: 230412 (C4 (Web Text))

Max Activating Token Index: 957

Text #10

Max Range: 1.5964. Min Range: -1.5964

Max Act: 1.0878. Min Act: -0.0000

Data Index: 318844 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 1.5964. Min Range: -1.5964

Max Act: 1.1279. Min Act: -0.0000

Data Index: 312145 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 1.5964. Min Range: -1.5964

Max Act: 1.0385. Min Act: -0.0000

Data Index: 977312 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 1.5964. Min Range: -1.5964

Max Act: 0.9687. Min Act: -0.0000

Data Index: 43329 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 1.5964. Min Range: -1.5964

Max Act: 1.0106. Min Act: -0.0000

Data Index: 977925 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 1.5964. Min Range: -1.5964

Max Act: 1.0146. Min Act: -0.0000

Data Index: 1183372 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 1.5964. Min Range: -1.5964

Max Act: 1.0069. Min Act: -0.0000

Data Index: 423687 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 1.5964. Min Range: -1.5964

Max Act: 0.9466. Min Act: -0.0000

Data Index: 321461 (C4 (Web Text))

Max Activating Token Index: 1004

Text #18

Max Range: 1.5964. Min Range: -1.5964

Max Act: 0.9786. Min Act: -0.0000

Data Index: 755286 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 1.5964. Min Range: -1.5964

Max Act: 0.9652. Min Act: -0.0000

Data Index: 1062464 (C4 (Web Text))

Max Activating Token Index: 863