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

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

Neuron 4667 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.6930. Min Act: -0.0002

Data Index: 1304148 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.5949. Min Act: -0.0002

Data Index: 949150 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.5844. Min Act: -0.0002

Data Index: 611888 (C4 (Web Text))

Max Activating Token Index: 658

Text #3

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.5801. Min Act: -0.0002

Data Index: 585459 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.5700. Min Act: -0.0002

Data Index: 975814 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.5810. Min Act: -0.0002

Data Index: 197252 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.5579. Min Act: -0.0002

Data Index: 29828 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.5549. Min Act: -0.0002

Data Index: 359886 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.5577. Min Act: -0.0003

Data Index: 690289 (C4 (Web Text))

Max Activating Token Index: 784

Text #9

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.5534. Min Act: -0.0003

Data Index: 280944 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.5369. Min Act: -0.0002

Data Index: 202389 (C4 (Web Text))

Max Activating Token Index: 532

Text #11

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.5511. Min Act: -0.0002

Data Index: 420785 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.5522. Min Act: -0.0002

Data Index: 172793 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.5292. Min Act: -0.0002

Data Index: 463117 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.5307. Min Act: -0.0002

Data Index: 985377 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.5330. Min Act: -0.0002

Data Index: 79599 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.5277. Min Act: -0.0002

Data Index: 800175 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.5290. Min Act: -0.0003

Data Index: 452794 (C4 (Web Text))

Max Activating Token Index: 525

Text #18

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.5247. Min Act: -0.0002

Data Index: 633837 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.5222. Min Act: -0.0002

Data Index: 112834 (C4 (Web Text))

Max Activating Token Index: 650