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

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

Neuron 3151 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: 0.2933. Min Range: -0.2933

Max Act: 0.2933. Min Act: -0.0001

Data Index: 1127550 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2609. Min Act: -0.0001

Data Index: 1186067 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2701. Min Act: -0.0001

Data Index: 902759 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2470. Min Act: -0.0001

Data Index: 845781 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2507. Min Act: -0.0001

Data Index: 154044 (C4 (Web Text))

Max Activating Token Index: 609

Text #5

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2222. Min Act: -0.0001

Data Index: 920093 (C4 (Web Text))

Max Activating Token Index: 784

Text #6

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2176. Min Act: -0.0001

Data Index: 700156 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2444. Min Act: -0.0001

Data Index: 739919 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2347. Min Act: -0.0001

Data Index: 1346150 (C4 (Web Text))

Max Activating Token Index: 579

Text #9

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2356. Min Act: -0.0001

Data Index: 980689 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2304. Min Act: -0.0001

Data Index: 78781 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2229. Min Act: -0.0001

Data Index: 755223 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2273. Min Act: -0.0001

Data Index: 123694 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2047. Min Act: -0.0001

Data Index: 256815 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2274. Min Act: -0.0001

Data Index: 917054 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2246. Min Act: -0.0001

Data Index: 280679 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2179. Min Act: -0.0001

Data Index: 135649 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2208. Min Act: -0.0001

Data Index: 992128 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2135. Min Act: -0.0001

Data Index: 430784 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2151. Min Act: -0.0001

Data Index: 975631 (C4 (Web Text))

Max Activating Token Index: 450