Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2056 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.6479. Min Act: -0.0001

Data Index: 1353007 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.6755. Min Act: -0.0001

Data Index: 722398 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.6375. Min Act: -0.0001

Data Index: 1568401 (Python Code)

Max Activating Token Index: 426

Text #3

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.5977. Min Act: -0.0001

Data Index: 1198774 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.6763. Min Act: -0.0001

Data Index: 260986 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.6383. Min Act: -0.0001

Data Index: 1324715 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.6120. Min Act: -0.0001

Data Index: 432292 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.5300. Min Act: -0.0001

Data Index: 800001 (C4 (Web Text))

Max Activating Token Index: 343

Text #8

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.5857. Min Act: -0.0001

Data Index: 1283305 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.5851. Min Act: -0.0001

Data Index: 797086 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.5587. Min Act: -0.0001

Data Index: 455749 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.4809. Min Act: -0.0001

Data Index: 439946 (C4 (Web Text))

Max Activating Token Index: 536

Text #12

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.5605. Min Act: -0.0001

Data Index: 1318374 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.5785. Min Act: -0.0001

Data Index: 51670 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.5398. Min Act: -0.0001

Data Index: 341917 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.5404. Min Act: -0.0001

Data Index: 371821 (C4 (Web Text))

Max Activating Token Index: 269

Text #16

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.5353. Min Act: -0.0001

Data Index: 1058303 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.5554. Min Act: -0.0001

Data Index: 1255978 (C4 (Web Text))

Max Activating Token Index: 217

Text #18

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.4656. Min Act: -0.0001

Data Index: 999906 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.5297. Min Act: -0.0001

Data Index: 647911 (C4 (Web Text))

Max Activating Token Index: 226