Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1933 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.7858. Min Act: -0.0000

Data Index: 74816 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.6753. Min Act: -0.0000

Data Index: 109360 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.5584. Min Act: -0.0000

Data Index: 621331 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.5757. Min Act: -0.0000

Data Index: 1292038 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.5115. Min Act: -0.0000

Data Index: 628437 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.4899. Min Act: -0.0000

Data Index: 438572 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.5043. Min Act: -0.0000

Data Index: 220946 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.4869. Min Act: -0.0000

Data Index: 402071 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.5167. Min Act: -0.0000

Data Index: 1151037 (C4 (Web Text))

Max Activating Token Index: 348

Text #9

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.4923. Min Act: -0.0000

Data Index: 317761 (C4 (Web Text))

Max Activating Token Index: 526

Text #10

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.4700. Min Act: -0.0000

Data Index: 760969 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.4337. Min Act: -0.0000

Data Index: 1315574 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.4459. Min Act: -0.0000

Data Index: 202095 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.4787. Min Act: -0.0000

Data Index: 1111922 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.4607. Min Act: -0.0000

Data Index: 14432 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.4498. Min Act: -0.0000

Data Index: 1468061 (Python Code)

Max Activating Token Index: 818

Text #16

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.4526. Min Act: -0.0000

Data Index: 97919 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.4489. Min Act: -0.0000

Data Index: 748424 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.4401. Min Act: -0.0000

Data Index: 1183946 (C4 (Web Text))

Max Activating Token Index: 813

Text #19

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.4328. Min Act: -0.0000

Data Index: 1140284 (C4 (Web Text))

Max Activating Token Index: 390