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

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

Neuron 5814 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: 4.2605. Min Range: -4.2605

Max Act: 3.8282. Min Act: -0.0000

Data Index: 1393490 (Python Code)

Max Activating Token Index: 808

Text #1

Max Range: 4.2605. Min Range: -4.2605

Max Act: 4.2605. Min Act: -0.0000

Data Index: 1485147 (Python Code)

Max Activating Token Index: 616

Text #2

Max Range: 4.2605. Min Range: -4.2605

Max Act: 4.0108. Min Act: -0.0000

Data Index: 1644469 (Python Code)

Max Activating Token Index: 291

Text #3

Max Range: 4.2605. Min Range: -4.2605

Max Act: 3.7477. Min Act: -0.0000

Data Index: 1624037 (Python Code)

Max Activating Token Index: 131

Text #4

Max Range: 4.2605. Min Range: -4.2605

Max Act: 3.4832. Min Act: -0.0000

Data Index: 849945 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 4.2605. Min Range: -4.2605

Max Act: 3.4447. Min Act: -0.0000

Data Index: 1425603 (Python Code)

Max Activating Token Index: 153

Text #6

Max Range: 4.2605. Min Range: -4.2605

Max Act: 3.3407. Min Act: -0.0000

Data Index: 115604 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 4.2605. Min Range: -4.2605

Max Act: 3.1152. Min Act: -0.0000

Data Index: 1174298 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 4.2605. Min Range: -4.2605

Max Act: 2.9405. Min Act: -0.0000

Data Index: 1644784 (Python Code)

Max Activating Token Index: 707

Text #9

Max Range: 4.2605. Min Range: -4.2605

Max Act: 3.0549. Min Act: -0.0000

Data Index: 331124 (C4 (Web Text))

Max Activating Token Index: 658

Text #10

Max Range: 4.2605. Min Range: -4.2605

Max Act: 3.0091. Min Act: -0.0000

Data Index: 1067034 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 4.2605. Min Range: -4.2605

Max Act: 2.9552. Min Act: -0.0000

Data Index: 889810 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 4.2605. Min Range: -4.2605

Max Act: 2.9267. Min Act: -0.0000

Data Index: 493947 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 4.2605. Min Range: -4.2605

Max Act: 2.8791. Min Act: -0.0000

Data Index: 199936 (C4 (Web Text))

Max Activating Token Index: 888

Text #14

Max Range: 4.2605. Min Range: -4.2605

Max Act: 2.8597. Min Act: -0.0000

Data Index: 1405466 (Python Code)

Max Activating Token Index: 172

Text #15

Max Range: 4.2605. Min Range: -4.2605

Max Act: 2.8253. Min Act: -0.0000

Data Index: 729827 (C4 (Web Text))

Max Activating Token Index: 234

Text #16

Max Range: 4.2605. Min Range: -4.2605

Max Act: 2.7777. Min Act: -0.0000

Data Index: 58435 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 4.2605. Min Range: -4.2605

Max Act: 2.7861. Min Act: -0.0000

Data Index: 733222 (C4 (Web Text))

Max Activating Token Index: 531

Text #18

Max Range: 4.2605. Min Range: -4.2605

Max Act: 2.7748. Min Act: -0.0000

Data Index: 1308835 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 4.2605. Min Range: -4.2605

Max Act: 2.6163. Min Act: -0.0000

Data Index: 1584058 (Python Code)

Max Activating Token Index: 821