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

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

Neuron 3821 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: 0.6441. Min Range: -0.6441

Max Act: 0.6441. Min Act: -0.0001

Data Index: 1535685 (Python Code)

Max Activating Token Index: 258

Text #1

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.5921. Min Act: -0.0001

Data Index: 1558224 (Python Code)

Max Activating Token Index: 252

Text #2

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.5785. Min Act: -0.0001

Data Index: 1502542 (Python Code)

Max Activating Token Index: 354

Text #3

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.5208. Min Act: -0.0001

Data Index: 1520185 (Python Code)

Max Activating Token Index: 808

Text #4

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.5145. Min Act: -0.0001

Data Index: 1623882 (Python Code)

Max Activating Token Index: 401

Text #5

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.5026. Min Act: -0.0001

Data Index: 1360459 (Python Code)

Max Activating Token Index: 781

Text #6

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.5027. Min Act: -0.0001

Data Index: 1434026 (Python Code)

Max Activating Token Index: 131

Text #7

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.4977. Min Act: -0.0001

Data Index: 1468595 (Python Code)

Max Activating Token Index: 502

Text #8

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.4776. Min Act: -0.0001

Data Index: 1471442 (Python Code)

Max Activating Token Index: 83

Text #9

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.4990. Min Act: -0.0000

Data Index: 1071381 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.4981. Min Act: -0.0001

Data Index: 1643266 (Python Code)

Max Activating Token Index: 968

Text #11

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.4627. Min Act: -0.0001

Data Index: 1540859 (Python Code)

Max Activating Token Index: 365

Text #12

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.4587. Min Act: -0.0000

Data Index: 1378471 (Python Code)

Max Activating Token Index: 661

Text #13

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.4516. Min Act: -0.0001

Data Index: 1554211 (Python Code)

Max Activating Token Index: 772

Text #14

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.4789. Min Act: -0.0001

Data Index: 1380837 (Python Code)

Max Activating Token Index: 514

Text #15

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.4603. Min Act: -0.0001

Data Index: 1633568 (Python Code)

Max Activating Token Index: 807

Text #16

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.4589. Min Act: -0.0001

Data Index: 1468563 (Python Code)

Max Activating Token Index: 896

Text #17

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.4577. Min Act: -0.0000

Data Index: 1054206 (C4 (Web Text))

Max Activating Token Index: 416

Text #18

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.4646. Min Act: -0.0001

Data Index: 1458835 (Python Code)

Max Activating Token Index: 257

Text #19

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.4491. Min Act: -0.0001

Data Index: 1414936 (Python Code)

Max Activating Token Index: 70