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

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

Neuron 2721 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: 0.6134. Min Range: -0.6134

Max Act: 0.6134. Min Act: -0.0001

Data Index: 491749 (C4 (Web Text))

Max Activating Token Index: 610

Text #1

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.5888. Min Act: -0.0000

Data Index: 299725 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4937. Min Act: -0.0000

Data Index: 407964 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.5095. Min Act: -0.0000

Data Index: 1269758 (C4 (Web Text))

Max Activating Token Index: 251

Text #4

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4619. Min Act: -0.0000

Data Index: 863972 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4463. Min Act: -0.0000

Data Index: 807983 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4187. Min Act: -0.0000

Data Index: 719684 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4733. Min Act: -0.0000

Data Index: 1165438 (C4 (Web Text))

Max Activating Token Index: 717

Text #8

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.3954. Min Act: -0.0000

Data Index: 249844 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4252. Min Act: -0.0000

Data Index: 32496 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4228. Min Act: -0.0000

Data Index: 1025184 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4333. Min Act: -0.0000

Data Index: 1244590 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4295. Min Act: -0.0000

Data Index: 1211457 (C4 (Web Text))

Max Activating Token Index: 537

Text #13

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4149. Min Act: -0.0000

Data Index: 669767 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.3985. Min Act: -0.0000

Data Index: 804268 (C4 (Web Text))

Max Activating Token Index: 241

Text #15

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4005. Min Act: -0.0000

Data Index: 90656 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.3806. Min Act: -0.0000

Data Index: 99827 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4082. Min Act: -0.0000

Data Index: 54176 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.3907. Min Act: -0.0000

Data Index: 429057 (C4 (Web Text))

Max Activating Token Index: 967

Text #19

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.3695. Min Act: -0.0000

Data Index: 49774 (C4 (Web Text))

Max Activating Token Index: 704