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

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

Neuron 1461 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2739. Min Act: -0.0001

Data Index: 316940 (C4 (Web Text))

Max Activating Token Index: 407

Text #1

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2657. Min Act: -0.0001

Data Index: 1039617 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2519. Min Act: -0.0001

Data Index: 326794 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2555. Min Act: 0.0001

Data Index: 5280 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2541. Min Act: -0.0000

Data Index: 229762 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2436. Min Act: 0.0001

Data Index: 459449 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2410. Min Act: -0.0000

Data Index: 1172384 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2387. Min Act: -0.0000

Data Index: 1027270 (C4 (Web Text))

Max Activating Token Index: 510

Text #8

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2308. Min Act: -0.0001

Data Index: 1379098 (Python Code)

Max Activating Token Index: 437

Text #9

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2354. Min Act: -0.0000

Data Index: 607477 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2291. Min Act: -0.0001

Data Index: 422495 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2260. Min Act: -0.0001

Data Index: 1216431 (C4 (Web Text))

Max Activating Token Index: 933

Text #12

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2180. Min Act: -0.0000

Data Index: 531940 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2254. Min Act: -0.0000

Data Index: 996557 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2206. Min Act: 0.0000

Data Index: 472239 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2208. Min Act: -0.0000

Data Index: 36497 (C4 (Web Text))

Max Activating Token Index: 916

Text #16

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2103. Min Act: -0.0001

Data Index: 349747 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2174. Min Act: -0.0001

Data Index: 1040117 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2182. Min Act: -0.0001

Data Index: 430002 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2176. Min Act: -0.0001

Data Index: 271416 (C4 (Web Text))

Max Activating Token Index: 150