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

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

Neuron 3869 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: 0.4135. Min Range: -0.4135

Max Act: 0.4135. Min Act: -0.0000

Data Index: 699961 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3785. Min Act: -0.0000

Data Index: 1562216 (Python Code)

Max Activating Token Index: 603

Text #2

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3851. Min Act: -0.0000

Data Index: 1546468 (Python Code)

Max Activating Token Index: 915

Text #3

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3533. Min Act: -0.0000

Data Index: 386097 (C4 (Web Text))

Max Activating Token Index: 950

Text #4

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3629. Min Act: -0.0000

Data Index: 1616248 (Python Code)

Max Activating Token Index: 803

Text #5

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3559. Min Act: -0.0000

Data Index: 646606 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3546. Min Act: -0.0000

Data Index: 1437805 (Python Code)

Max Activating Token Index: 393

Text #7

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3127. Min Act: -0.0000

Data Index: 1650354 (Python Code)

Max Activating Token Index: 1015

Text #8

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3399. Min Act: -0.0000

Data Index: 1408309 (Python Code)

Max Activating Token Index: 204

Text #9

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3388. Min Act: -0.0000

Data Index: 1258192 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3092. Min Act: -0.0000

Data Index: 1600854 (Python Code)

Max Activating Token Index: 1017

Text #11

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3314. Min Act: -0.0000

Data Index: 1607971 (Python Code)

Max Activating Token Index: 475

Text #12

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3046. Min Act: -0.0000

Data Index: 1524753 (Python Code)

Max Activating Token Index: 419

Text #13

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3132. Min Act: -0.0000

Data Index: 1540645 (Python Code)

Max Activating Token Index: 39

Text #14

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3114. Min Act: -0.0000

Data Index: 270252 (C4 (Web Text))

Max Activating Token Index: 658

Text #15

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3235. Min Act: -0.0000

Data Index: 1537944 (Python Code)

Max Activating Token Index: 703

Text #16

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3124. Min Act: -0.0000

Data Index: 1443210 (Python Code)

Max Activating Token Index: 18

Text #17

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3181. Min Act: -0.0000

Data Index: 336375 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3346. Min Act: -0.0000

Data Index: 1510342 (Python Code)

Max Activating Token Index: 680

Text #19

Max Range: 0.4135. Min Range: -0.4135

Max Act: 0.3146. Min Act: -0.0000

Data Index: 119914 (C4 (Web Text))

Max Activating Token Index: 640