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

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

Neuron 1746 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.4733. Min Act: -0.0001

Data Index: 1366539 (Python Code)

Max Activating Token Index: 200

Text #1

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.4350. Min Act: -0.0001

Data Index: 1439945 (Python Code)

Max Activating Token Index: 122

Text #2

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.4114. Min Act: -0.0001

Data Index: 391168 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.4261. Min Act: -0.0001

Data Index: 281968 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.4114. Min Act: -0.0001

Data Index: 1073290 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.4367. Min Act: -0.0001

Data Index: 613136 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.4211. Min Act: -0.0001

Data Index: 259029 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3951. Min Act: -0.0001

Data Index: 46771 (C4 (Web Text))

Max Activating Token Index: 683

Text #8

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3754. Min Act: -0.0001

Data Index: 1195773 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3968. Min Act: -0.0001

Data Index: 1402822 (Python Code)

Max Activating Token Index: 61

Text #10

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.4136. Min Act: -0.0001

Data Index: 336442 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3950. Min Act: -0.0001

Data Index: 901141 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3820. Min Act: -0.0001

Data Index: 1615950 (Python Code)

Max Activating Token Index: 997

Text #13

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3913. Min Act: -0.0001

Data Index: 1504965 (Python Code)

Max Activating Token Index: 156

Text #14

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3757. Min Act: -0.0001

Data Index: 1387087 (Python Code)

Max Activating Token Index: 98

Text #15

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3572. Min Act: -0.0001

Data Index: 498260 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3657. Min Act: -0.0001

Data Index: 1629873 (Python Code)

Max Activating Token Index: 882

Text #17

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3656. Min Act: -0.0001

Data Index: 1622229 (Python Code)

Max Activating Token Index: 277

Text #18

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3761. Min Act: -0.0001

Data Index: 1077530 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3488. Min Act: -0.0001

Data Index: 262394 (C4 (Web Text))

Max Activating Token Index: 159